{ "schema": "modelrater-or-slices/1", "portal": "https://mdata.modelraters.com", "source_url": "https://openrouter.ai/api/v1/benchmarks", "as_of": "2026-10-27T03:32:35.022Z", "citation": "Attribute each slice by its source field. The mixed pull has a null citation.", "window": { "from": "2026-04-27", "through": "2026-10-27", "cap": 250, "model_count": 135, "with_any_score": 90, "with_no_score": 45, "rule": "Text-output models from openrouter_live.json created on or after 2026-04-27, newest first, cap 250. Aliases, batch twins, free twins, and routers are out. A benchmark row joins when model_permaslug equals canonical_slug or id, or is that id plus a date." }, "slice_count": 50, "model_count": 135, "models": [ { "catalog_id": "openai/gpt-6.1-terra-pro", "name": "OpenAI: GPT-6.1 Terra Pro", "maker": "openai", "created": 1793038556, "scored_slices": [] }, { "catalog_id": "openai/gpt-6.1-terra", "name": "OpenAI: GPT-6.1 Terra", "maker": "openai", "created": 1793038409, "scored_slices": [ "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost" ] }, { "catalog_id": "moonshotai/kimi-k3.1-pro", "name": "MoonshotAI: Kimi K3.1 Pro", "maker": "moonshotai", "created": 1792778188, "scored_slices": [ "aa-intelligence", "da-models-3d", "da-models-3d-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost" ] }, { "catalog_id": "minimax/minimax-m3.1-flash", "name": "MiniMax: MiniMax M3.1 Flash", "maker": "minimax", "created": 1792379569, "scored_slices": [ "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek: DeepSeek V4.1 Flash 1017", "maker": "deepseek", "created": 1792225624, "scored_slices": [ "aa-intelligence", "da-agents-spreadsheet", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "elorian/glimpse", "name": "Elorian: Glimpse", "maker": "elorian", "created": 1792206629, "scored_slices": [] }, { "catalog_id": "reflection/beam-1.0-501b-a23b", "name": "Reflection: Beam 1.0 501B A23B", "maker": "reflection", "created": 1792160499, "scored_slices": [ "da-models-codecategories", "da-models-codecategories-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "inception/mercury-3", "name": "Inception: Mercury 3", "maker": "inception", "created": 1792158337, "scored_slices": [ "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed" ] }, { "catalog_id": "moondream/moondream3-preview", "name": "Moondream: Moondream 3 Preview", "maker": "moondream", "created": 1792102385, "scored_slices": [] }, { "catalog_id": "moondream/moondream3.1-9b-a2b", "name": "Moondream: Moondream 3.1", "maker": "moondream", "created": 1792102373, "scored_slices": [] }, { "catalog_id": "meta/muse-spark-open", "name": "Meta: Muse Spark Open", "maker": "meta", "created": 1792087069, "scored_slices": [ "da-models-codecategories", "da-models-codecategories-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "nvidia/nemotron-3.5-super-vl", "name": "NVIDIA: Nemotron 3.5 Super VL", "maker": "nvidia", "created": 1792076662, "scored_slices": [ "aa-intelligence", "da-models-3d", "da-models-3d-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "unbiased/pareto-26.10", "name": "Pareto 26.10", "maker": "unbiased", "created": 1792073620, "scored_slices": [] }, { "catalog_id": "unbiased/pareto-26.9", "name": "Pareto 26.9", "maker": "unbiased", "created": 1791930537, "scored_slices": [] }, { "catalog_id": "liquid/lfm-2.5-24b-a2b", "name": "LiquidAI: LFM2.5-24B-A2B", "maker": "liquid", "created": 1791912025, "scored_slices": [] }, { "catalog_id": "google/gemini-4-argon", "name": "Google: Gemini 4 Argon", "maker": "google", "created": 1791907477, "scored_slices": [ "aa-intelligence", "da-agents-blender3d", "da-agents-spreadsheet", "da-models-3d", "da-models-3d-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "scaledown/summarize", "name": "ScaleDown: Summarize", "maker": "scaledown", "created": 1791893360, "scored_slices": [] }, { "catalog_id": "scaledown/extract", "name": "ScaleDown: Extract", "maker": "scaledown", "created": 1791893351, "scored_slices": [] }, { "catalog_id": "meta/muse-wonder", "name": "Meta: Muse Wonder", "maker": "meta", "created": 1791807945, "scored_slices": [ "da-agents-blender3d", "da-agents-htmlslides", "da-agents-python-pptxslides", "da-agents-spreadsheet", "da-models-3d", "da-models-3d-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed" ] }, { "catalog_id": "stepfun/step-5-preview", "name": "StepFun: Step 5 Preview", "maker": "stepfun", "created": 1791462849, "scored_slices": [ "aa-intelligence" ] }, { "catalog_id": "anthropic/claude-haiku-5.5", "name": "Anthropic: Claude Haiku 5.5", "maker": "anthropic", "created": 1791397883, "scored_slices": [ "aa-intelligence", "da-models-3d", "da-models-3d-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "google/gemini-nano-banana-2.1", "name": "Google: Nano Banana 2.1", "maker": "google", "created": 1791300825, "scored_slices": [] }, { "catalog_id": "mistralai/mistral-large-4-0", "name": "Mistral: Mistral Large 4", "maker": "mistralai", "created": 1791294122, "scored_slices": [ "aa-intelligence", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed" ] }, { "catalog_id": "inclusionai/ling-3.1-flash", "name": "inclusionAI: Ling 3.1 Flash", "maker": "inclusionai", "created": 1790950024, "scored_slices": [ "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "openai/gpt-6.1-sol-pro", "name": "OpenAI: GPT-6.1 Sol Pro", "maker": "openai", "created": 1790702886, "scored_slices": [] }, { "catalog_id": "openai/gpt-6.1-sol", "name": "OpenAI: GPT-6.1 Sol", "maker": "openai", "created": 1790702882, "scored_slices": [ "aa-intelligence", "da-agents-blender3d", "da-agents-mobileapps", "da-agents-spreadsheet", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Anthropic: Claude Sonnet 5.5", "maker": "anthropic", "created": 1790618686, "scored_slices": [ "aa-intelligence", "da-agents-blender3d", "da-agents-mobileapps", "da-agents-spreadsheet", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "perceptron/perceptron-mk1.5", "name": "Perceptron: Perceptron Mk1.5", "maker": "perceptron", "created": 1790352661, "scored_slices": [] }, { "catalog_id": "fireworks/ember-1", "name": "Fireworks: Ember-1", "maker": "fireworks", "created": 1790208461, "scored_slices": [] }, { "catalog_id": "z-ai/glm-5.3-prime", "name": "Z.ai: GLM 5.3 Prime", "maker": "z-ai", "created": 1790199651, "scored_slices": [] }, { "catalog_id": "qwen/qwen3.8-max-prime", "name": "Qwen: Qwen3.8 Max Prime", "maker": "qwen", "created": 1790191228, "scored_slices": [] }, { "catalog_id": "aion-labs/aion-3.5-mini", "name": "AionLabs: Aion 3.5 Mini", "maker": "aion-labs", "created": 1790170962, "scored_slices": [] }, { "catalog_id": "aion-labs/aion-3.5", "name": "AionLabs: Aion 3.5", "maker": "aion-labs", "created": 1790170961, "scored_slices": [] }, { "catalog_id": "upstage/solar-mini4", "name": "Upstage: Solar Mini 4", "maker": "upstage", "created": 1790160358, "scored_slices": [ "aa-intelligence", "da-models-3d", "da-models-3d-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed" ] }, { "catalog_id": "cohere/command-a-plus", "name": "Cohere: Command A+", "maker": "cohere", "created": 1790102896, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence" ] }, { "catalog_id": "openai/gpt-6-luna-pro", "name": "OpenAI: GPT-6 Luna Pro", "maker": "openai", "created": 1790100791, "scored_slices": [ "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "openai/gpt-6-luna", "name": "OpenAI: GPT-6 Luna", "maker": "openai", "created": 1790100786, "scored_slices": [ "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "openai/gpt-6-sol-pro", "name": "OpenAI: GPT-6 Sol Pro", "maker": "openai", "created": 1790100781, "scored_slices": [] }, { "catalog_id": "openai/gpt-6-sol", "name": "OpenAI: GPT-6 Sol", "maker": "openai", "created": 1790100775, "scored_slices": [ "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "anthropic/claude-opus-5.5", "name": "Anthropic: Claude Opus 5.5", "maker": "anthropic", "created": 1790094732, "scored_slices": [ "aa-intelligence", "da-agents-blender3d", "da-agents-mobileapps", "da-agents-spreadsheet", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "nvidia/switchyard", "name": "NVIDIA: Switchyard", "maker": "nvidia", "created": 1790025947, "scored_slices": [ "or-gpqa_diamond", "or-gpqa_diamond-cost" ] }, { "catalog_id": "xiaomi/mimo-v2.6-pro-ultraspeed", "name": "Xiaomi: MiMo-V2.6-Pro-UltraSpeed", "maker": "xiaomi", "created": 1790021267, "scored_slices": [] }, { "catalog_id": "xiaomi/mimo-v2.6-flash", "name": "Xiaomi: MiMo-V2.6-Flash", "maker": "xiaomi", "created": 1790021264, "scored_slices": [ "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "Xiaomi: MiMo-V2.6-Pro", "maker": "xiaomi", "created": 1790021259, "scored_slices": [ "aa-intelligence", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "x-ai/grok-4.7", "name": "SpaceXAI: Grok 4.7", "maker": "x-ai", "created": 1790007541, "scored_slices": [ "aa-intelligence", "da-models-3d", "da-models-3d-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed" ] }, { "catalog_id": "qwen/qwen3.8-omni-flash", "name": "Qwen: Qwen3.8 Omni Flash", "maker": "qwen", "created": 1789959954, "scored_slices": [] }, { "catalog_id": "prism-ml/ternary-bonsai-2-27b", "name": "PrismML: Ternary Bonsai 2 27B", "maker": "prism-ml", "created": 1789754046, "scored_slices": [] }, { "catalog_id": "z-ai/glm-5.3-flashx", "name": "Z.ai: GLM 5.3 FlashX", "maker": "z-ai", "created": 1789744020, "scored_slices": [] }, { "catalog_id": "inference-net/schematron-v2-turbo", "name": "Inference.net: Schematron V2 Turbo", "maker": "inference-net", "created": 1789176949, "scored_slices": [] }, { "catalog_id": "inference-net/schematron-v2-small", "name": "Inference.net: Schematron V2 Small", "maker": "inference-net", "created": 1789176933, "scored_slices": [] }, { "catalog_id": "sakana/fugu-ultra-v2", "name": "Sakana: Fugu Ultra v2", "maker": "sakana", "created": 1789105383, "scored_slices": [ "or-gpqa_diamond", "or-gpqa_diamond-cost" ] }, { "catalog_id": "sakana/fugu-max", "name": "Sakana: Fugu Max", "maker": "sakana", "created": 1789104771, "scored_slices": [ "or-gpqa_diamond", "or-gpqa_diamond-cost" ] }, { "catalog_id": "inclusionai/ling-3.0-flash-vl", "name": "inclusionAI: Ling 3.0 Flash VL", "maker": "inclusionai", "created": 1789056114, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "deepseek/deepseek-v4.1-flash", "name": "DeepSeek: DeepSeek V4.1 Flash", "maker": "deepseek", "created": 1789021285, "scored_slices": [ "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "inception/mercury-2.5", "name": "Inception: Mercury 2.5", "maker": "inception", "created": 1788892137, "scored_slices": [ "aa-intelligence" ] }, { "catalog_id": "nex-agi/nex-n2.5-mini", "name": "Nex AGI: Nex-N2.5-Mini", "maker": "nex-agi", "created": 1788890061, "scored_slices": [] }, { "catalog_id": "nex-agi/nex-n2.5-pro", "name": "Nex AGI: Nex-N2.5-Pro", "maker": "nex-agi", "created": 1788890050, "scored_slices": [] }, { "catalog_id": "openai/gpt-6-astra", "name": "OpenAI: GPT-6 Astra", "maker": "openai", "created": 1788552838, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "openai/gpt-6-astra-pro", "name": "OpenAI: GPT-6 Astra Pro", "maker": "openai", "created": 1788552835, "scored_slices": [ "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "qwen/qwen3.8-max-0902", "name": "Qwen: Qwen3.8 Max (0902)", "maker": "qwen", "created": 1788469704, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence" ] }, { "catalog_id": "meta/muse-spark-1.3-contributor", "name": "Meta: Muse Spark 1.3 Contributor", "maker": "meta", "created": 1788381519, "scored_slices": [] }, { "catalog_id": "meta/muse-spark-1.3", "name": "Meta: Muse Spark 1.3", "maker": "meta", "created": 1788378359, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-agents-blender3d", "da-agents-fullstack", "da-agents-godotgamedev", "da-agents-mobileapps", "da-agents-python-pptxslides", "da-agents-spreadsheet", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed" ] }, { "catalog_id": "google/gemini-3.8-flash", "name": "Google: Gemini 3.8 Flash", "maker": "google", "created": 1788362056, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-agents-androidnative", "da-agents-blender3d", "da-agents-fullstack", "da-agents-godotgamedev", "da-agents-mobileapps", "da-agents-python-pptxslides", "da-agents-spreadsheet", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "anthropic/claude-fable-5.1", "name": "Anthropic: Claude Fable 5.1", "maker": "anthropic", "created": 1788285838, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-agents-fullstack", "da-agents-godotgamedev", "da-agents-htmlslides", "da-agents-mobileapps", "da-agents-python-pptxslides", "da-agents-spreadsheet", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "ibm-granite/granite-4.2-8b", "name": "IBM: Granite 4.2 8B", "maker": "ibm-granite", "created": 1788206780, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "tencent/hy4-preview", "name": "Tencent: Hy4 preview", "maker": "tencent", "created": 1787897375, "scored_slices": [ "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "qwen/qwen3.8-flash", "name": "Qwen: Qwen3.8 Flash", "maker": "qwen", "created": 1787773060, "scored_slices": [ "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "z-ai/glm-5.3-flash", "name": "Z.ai: GLM 5.3 Flash", "maker": "z-ai", "created": 1787752741, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "meta/muse-spark-1.2-contributor", "name": "Meta: Muse Spark 1.2 Contributor", "maker": "meta", "created": 1787336476, "scored_slices": [] }, { "catalog_id": "deepseek/deepseek-v4-flash-vision-exp", "name": "DeepSeek: DeepSeek V4 Flash Vision Exp", "maker": "deepseek", "created": 1787311563, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "tencent/hy-mt2-1.8b", "name": "Tencent: Hy-MT2-1.8B", "maker": "tencent", "created": 1787231581, "scored_slices": [] }, { "catalog_id": "tencent/hy-mt2-30b-a3b", "name": "Tencent: Hy-MT2-30B-A3B", "maker": "tencent", "created": 1787231561, "scored_slices": [ "or-gpqa_diamond", "or-gpqa_diamond-cost" ] }, { "catalog_id": "tencent/hy-mt2-7b", "name": "Tencent: Hy-MT2-7B", "maker": "tencent", "created": 1787148797, "scored_slices": [] }, { "catalog_id": "z-ai/glm-5.3", "name": "Z.ai: GLM 5.3", "maker": "z-ai", "created": 1787086655, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-agents-htmlslides", "da-agents-mobileapps", "da-agents-python-pptxslides", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "qwen/qwen3.8-27b", "name": "Qwen: Qwen3.8 27B", "maker": "qwen", "created": 1786722910, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "google/gemini-3.7-flash", "name": "Google: Gemini 3.7 Flash", "maker": "google", "created": 1786640581, "scored_slices": [ "aa-coding", "aa-intelligence", "da-agents-agenticgamedev", "da-agents-androidnative", "da-agents-blender3d", "da-agents-fullstack", "da-agents-godotgamedev", "da-agents-mobileapps", "da-agents-spreadsheet", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "bytedance-seed/seed-2-1-turbo", "name": "ByteDance Seed: Seed 2.1 Turbo", "maker": "bytedance-seed", "created": 1786552176, "scored_slices": [] }, { "catalog_id": "qwen/qwen3.8-2.4t-a95b", "name": "Qwen: Qwen3.8 2.4T A95B", "maker": "qwen", "created": 1786551702, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "bytedance-seed/seed-2.0-code", "name": "ByteDance Seed: Seed-2.0-Code", "maker": "bytedance-seed", "created": 1786550701, "scored_slices": [] }, { "catalog_id": "deepseek/deepseek-v4-pro-0813", "name": "DeepSeek: DeepSeek V4 Pro 0813", "maker": "deepseek", "created": 1786549364, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "x-ai/grok-4.6", "name": "SpaceXAI: Grok 4.6", "maker": "x-ai", "created": 1786548957, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-agents-agenticgamedev", "da-agents-androidnative", "da-agents-blender3d", "da-agents-fullstack", "da-agents-godotgamedev", "da-agents-htmlslides", "da-agents-mobileapps", "da-agents-python-pptxslides", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "liquid/lfm-2.5-2.6b", "name": "LiquidAI: LFM2.5-2.6B", "maker": "liquid", "created": 1786470519, "scored_slices": [ "aa-coding", "aa-intelligence" ] }, { "catalog_id": "nvidia/nemotron-3.5-lightning", "name": "NVIDIA: Nemotron 3.5 Lightning", "maker": "nvidia", "created": 1786452751, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "sakana/sakana-namazu", "name": "Sakana: Sakana Namazu", "maker": "sakana", "created": 1786410129, "scored_slices": [] }, { "catalog_id": "upstage/solar-pro4", "name": "Upstage: Solar Pro 4", "maker": "upstage", "created": 1786371636, "scored_slices": [ "aa-coding", "aa-intelligence", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed" ] }, { "catalog_id": "meta/muse-glimmer-30b", "name": "Meta: Muse Glimmer 30B", "maker": "meta", "created": 1786302394, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-models-gamedev", "da-models-gamedev-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "meta/muse-spark-1.2", "name": "Meta: Muse Spark 1.2", "maker": "meta", "created": 1785959287, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-agents-agenticgamedev", "da-agents-androidnative", "da-agents-blender3d", "da-agents-fullstack", "da-agents-htmlslides", "da-agents-mobileapps", "da-agents-python-pptxslides", "da-agents-spreadsheet", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed" ] }, { "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek: DeepSeek V4 Flash 0731", "maker": "deepseek", "created": 1785478908, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-search_browsecomp", "or-search_browsecomp-cost", "or-search_browsecomp-latency", "or-search_dsqa", "or-search_dsqa-cost", "or-search_dsqa-latency", "or-search_widesearch", "or-search_widesearch-cost", "or-search_widesearch-latency", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "thinkingmachines/inkling-small", "name": "Thinking Machines: Inkling Small", "maker": "thinkingmachines", "created": 1785443117, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "qwen/qwen3.7-flash", "name": "Qwen: Qwen3.7 Flash", "maker": "qwen", "created": 1785190561, "scored_slices": [] }, { "catalog_id": "anthropic/claude-opus-5", "name": "Anthropic: Claude Opus 5", "maker": "anthropic", "created": 1784912544, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-agents-agenticgamedev", "da-agents-androidnative", "da-agents-blender3d", "da-agents-fullstack", "da-agents-godotgamedev", "da-agents-mobileapps", "da-agents-python-pptxslides", "da-agents-spreadsheet", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-search_browsecomp", "or-search_browsecomp-cost", "or-search_browsecomp-latency", "or-search_dsqa", "or-search_dsqa-cost", "or-search_dsqa-latency", "or-search_hle", "or-search_hle-cost", "or-search_hle-latency", "or-search_widesearch", "or-search_widesearch-cost", "or-search_widesearch-latency", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "inclusionai/ling-3.0-flash", "name": "inclusionAI: Ling 3.0 Flash", "maker": "inclusionai", "created": 1784818580, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "poolside/laguna-s-2.1", "name": "Poolside: Laguna S 2.1", "maker": "poolside", "created": 1784652683, "scored_slices": [] }, { "catalog_id": "google/gemini-3.6-flash", "name": "Google: Gemini 3.6 Flash", "maker": "google", "created": 1784646733, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-agents-agenticgamedev", "da-agents-androidnative", "da-agents-blender3d", "da-agents-fullstack", "da-agents-htmlslides", "da-agents-mobileapps", "da-agents-python-pptxslides", "da-agents-spreadsheet", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "google/gemini-3.5-flash-lite", "name": "Google: Gemini 3.5 Flash Lite", "maker": "google", "created": 1784646726, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "meituan/longcat-2.0", "name": "Meituan: LongCat 2.0", "maker": "meituan", "created": 1784554658, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence" ] }, { "catalog_id": "thinkingmachines/inkling", "name": "Thinking Machines: Inkling", "maker": "thinkingmachines", "created": 1784325956, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "moonshotai/kimi-k3", "name": "MoonshotAI: Kimi K3", "maker": "moonshotai", "created": 1784215858, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-agents-agenticgamedev", "da-agents-androidnative", "da-agents-blender3d", "da-agents-fullstack", "da-agents-godotgamedev", "da-agents-htmlslides", "da-agents-mobileapps", "da-agents-python-pptxslides", "da-agents-spreadsheet", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "meta/muse-spark-1.1", "name": "Meta: Muse Spark 1.1", "maker": "meta", "created": 1784215741, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-agents-agenticgamedev", "da-agents-androidnative", "da-agents-blender3d", "da-agents-fullstack", "da-agents-godotgamedev", "da-agents-htmlslides", "da-agents-mobileapps", "da-agents-python-pptxslides", "da-agents-spreadsheet", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed" ] }, { "catalog_id": "openai/gpt-5.6-luna-pro", "name": "OpenAI: GPT-5.6 Luna Pro", "maker": "openai", "created": 1783590867, "scored_slices": [ "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "openai/gpt-5.6-luna", "name": "OpenAI: GPT-5.6 Luna", "maker": "openai", "created": 1783590864, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-search_browsecomp", "or-search_browsecomp-cost", "or-search_browsecomp-latency", "or-search_dsqa", "or-search_dsqa-cost", "or-search_dsqa-latency", "or-search_widesearch", "or-search_widesearch-cost", "or-search_widesearch-latency", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "openai/gpt-5.6-terra-pro", "name": "OpenAI: GPT-5.6 Terra Pro", "maker": "openai", "created": 1783590861, "scored_slices": [] }, { "catalog_id": "openai/gpt-5.6-terra", "name": "OpenAI: GPT-5.6 Terra", "maker": "openai", "created": 1783590857, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "openai/gpt-5.6-sol-pro", "name": "OpenAI: GPT-5.6 Sol Pro", "maker": "openai", "created": 1783590854, "scored_slices": [ "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "openai/gpt-5.6-sol", "name": "OpenAI: GPT-5.6 Sol", "maker": "openai", "created": 1783590850, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-search_browsecomp", "or-search_browsecomp-cost", "or-search_browsecomp-latency", "or-search_dsqa", "or-search_dsqa-cost", "or-search_dsqa-latency", "or-search_hle", "or-search_hle-cost", "or-search_hle-latency", "or-search_widesearch", "or-search_widesearch-cost", "or-search_widesearch-latency", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "x-ai/grok-4.5", "name": "SpaceXAI: Grok 4.5", "maker": "x-ai", "created": 1783523154, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-agents-agenticgamedev", "da-agents-androidnative", "da-agents-blender3d", "da-agents-fullstack", "da-agents-godotgamedev", "da-agents-htmlslides", "da-agents-mobileapps", "da-agents-python-pptxslides", "da-agents-spreadsheet", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed" ] }, { "catalog_id": "aion-labs/aion-3.0-mini", "name": "AionLabs: Aion-3.0-Mini", "maker": "aion-labs", "created": 1783443096, "scored_slices": [] }, { "catalog_id": "aion-labs/aion-3.0", "name": "AionLabs: Aion-3.0", "maker": "aion-labs", "created": 1783443095, "scored_slices": [] }, { "catalog_id": "tencent/hy3", "name": "Tencent: Hy3", "maker": "tencent", "created": 1783344048, "scored_slices": [ "da-models-3d", "da-models-3d-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed" ] }, { "catalog_id": "poolside/laguna-xs-2.1", "name": "Poolside: Laguna XS 2.1", "maker": "poolside", "created": 1783002429, "scored_slices": [] }, { "catalog_id": "anthropic/claude-sonnet-5", "name": "Anthropic: Claude Sonnet 5", "maker": "anthropic", "created": 1782843083, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-agents-agenticgamedev", "da-agents-androidnative", "da-agents-blender3d", "da-agents-fullstack", "da-agents-godotgamedev", "da-agents-htmlslides", "da-agents-mobileapps", "da-agents-python-pptxslides", "da-agents-spreadsheet", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "google/gemini-3.1-flash-lite-image", "name": "Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)", "maker": "google", "created": 1782837225, "scored_slices": [ "or-gpqa_diamond", "or-gpqa_diamond-cost" ] }, { "catalog_id": "sakana/fugu-ultra", "name": "Sakana: Fugu Ultra", "maker": "sakana", "created": 1782276303, "scored_slices": [ "or-gpqa_diamond", "or-gpqa_diamond-cost" ] }, { "catalog_id": "google/gemini-3.1-flash-image", "name": "Google: Nano Banana 2 (Gemini 3.1 Flash Image)", "maker": "google", "created": 1781754065, "scored_slices": [] }, { "catalog_id": "google/gemini-3-pro-image", "name": "Google: Nano Banana Pro (Gemini 3 Pro Image)", "maker": "google", "created": 1781754054, "scored_slices": [] }, { "catalog_id": "z-ai/glm-5.2", "name": "Z.ai: GLM 5.2", "maker": "z-ai", "created": 1781631930, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-agents-agenticgamedev", "da-agents-androidnative", "da-agents-fullstack", "da-agents-godotgamedev", "da-agents-htmlslides", "da-agents-mobileapps", "da-agents-python-pptxslides", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "moonshotai/kimi-k2.7-code", "name": "MoonshotAI: Kimi K2.7 Code", "maker": "moonshotai", "created": 1781266361, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-agents-agenticgamedev", "da-agents-androidnative", "da-agents-fullstack", "da-agents-godotgamedev", "da-agents-htmlslides", "da-agents-mobileapps", "da-agents-python-pptxslides", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "anthropic/claude-fable-5", "name": "Anthropic: Claude Fable 5", "maker": "anthropic", "created": 1781007515, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-agents-agenticgamedev", "da-agents-agentichtmlslides", "da-agents-agenticslides(html)", "da-agents-androidnative", "da-agents-fullstack", "da-agents-godotgamedev", "da-agents-htmlslides", "da-agents-mobileapps", "da-agents-python-pptxslides", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "nvidia/nemotron-3.5-content-safety", "name": "NVIDIA: Nemotron 3.5 Content Safety", "maker": "nvidia", "created": 1780581864, "scored_slices": [] }, { "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "NVIDIA: Nemotron 3 Ultra", "maker": "nvidia", "created": 1780551208, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen: Qwen3.7 Plus", "maker": "qwen", "created": 1780491783, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "minimax/minimax-m3", "name": "MiniMax: MiniMax M3", "maker": "minimax", "created": 1780245374, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-agents-agenticgamedev", "da-agents-androidnative", "da-agents-blender3d", "da-agents-fullstack", "da-agents-htmlslides", "da-agents-mobileapps", "da-agents-python-pptxslides", "da-agents-spreadsheet", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "stepfun/step-3.7-flash", "name": "StepFun: Step 3.7 Flash", "maker": "stepfun", "created": 1779985069, "scored_slices": [ "aa-coding", "aa-intelligence", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed" ] }, { "catalog_id": "anthropic/claude-opus-4.8", "name": "Anthropic: Claude Opus 4.8", "maker": "anthropic", "created": 1779905091, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-agents-agenticgamedev", "da-agents-agentichtmlslides", "da-agents-agenticslides", "da-agents-agenticslides(html)", "da-agents-agenticslides(python-pptx)", "da-agents-androidnative", "da-agents-blender3d", "da-agents-fullstack", "da-agents-godotgamedev", "da-agents-htmlslides", "da-agents-mobileapps", "da-agents-pptxslides", "da-agents-python-pptxslides", "da-agents-spreadsheet", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "qwen/qwen3.7-max", "name": "Qwen: Qwen3.7 Max", "maker": "qwen", "created": 1779376861, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-agents-agenticgamedev", "da-agents-androidnative", "da-agents-blender3d", "da-agents-fullstack", "da-agents-godotgamedev", "da-agents-htmlslides", "da-agents-mobileapps", "da-agents-python-pptxslides", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "x-ai/grok-build-0.1", "name": "SpaceXAI: Grok Build 0.1", "maker": "x-ai", "created": 1779298123, "scored_slices": [ "aa-coding", "aa-intelligence" ] }, { "catalog_id": "google/gemini-3.5-flash", "name": "Google: Gemini 3.5 Flash", "maker": "google", "created": 1779193800, "scored_slices": [ "aa-intelligence", "da-agents-agenticgamedev", "da-agents-agentichtmlslides", "da-agents-agenticslides", "da-agents-agenticslides(html)", "da-agents-agenticslides(python-pptx)", "da-agents-androidnative", "da-agents-blender3d", "da-agents-fullstack", "da-agents-godotgamedev", "da-agents-htmlslides", "da-agents-mobileapps", "da-agents-pptxslides", "da-agents-python-pptxslides", "da-agents-spreadsheet", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "perceptron/perceptron-mk1", "name": "Perceptron: Perceptron Mk1", "maker": "perceptron", "created": 1778597029, "scored_slices": [] }, { "catalog_id": "google/gemini-3.1-flash-lite", "name": "Google: Gemini 3.1 Flash Lite", "maker": "google", "created": 1778168828, "scored_slices": [ "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "x-ai/grok-4.3", "name": "SpaceXAI: Grok 4.3", "maker": "x-ai", "created": 1777591821, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "da-agents-agenticgamedev", "da-agents-agentichtmlslides", "da-agents-agenticslides", "da-agents-agenticslides(html)", "da-agents-agenticslides(python-pptx)", "da-agents-androidnative", "da-agents-blender3d", "da-agents-fullstack", "da-agents-godotgamedev", "da-agents-htmlslides", "da-agents-mobileapps", "da-agents-pptxslides", "da-agents-python-pptxslides", "da-agents-spreadsheet", "da-agents-webapps", "da-models-3d", "da-models-3d-speed", "da-models-asciiart", "da-models-asciiart-speed", "da-models-codecategories", "da-models-codecategories-speed", "da-models-dataviz", "da-models-dataviz-speed", "da-models-gamedev", "da-models-gamedev-speed", "da-models-svg", "da-models-svg-speed", "da-models-uicomponent", "da-models-uicomponent-speed", "da-models-website", "da-models-website-speed" ] }, { "catalog_id": "mistralai/mistral-medium-3-5", "name": "Mistral: Mistral Medium 3.5", "maker": "mistralai", "created": 1777570439, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence" ] }, { "catalog_id": "qwen/qwen3.5-plus-20260420", "name": "Qwen: Qwen3.5 Plus 2026-04-20", "maker": "qwen", "created": 1777261368, "scored_slices": [] }, { "catalog_id": "qwen/qwen3.6-flash", "name": "Qwen: Qwen3.6 Flash", "maker": "qwen", "created": 1777261362, "scored_slices": [] }, { "catalog_id": "qwen/qwen3.6-35b-a3b", "name": "Qwen: Qwen3.6 35B A3B", "maker": "qwen", "created": 1777260255, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] }, { "catalog_id": "qwen/qwen3.6-27b", "name": "Qwen: Qwen3.6 27B", "maker": "qwen", "created": 1777255064, "scored_slices": [ "aa-agentic", "aa-coding", "aa-intelligence", "or-gpqa_diamond", "or-gpqa_diamond-cost", "or-tau_bench_verified_airline", "or-tau_bench_verified_airline-cost" ] } ], "slices": [ { "ranked_count": 72, "scored_count": 72, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Claude Opus 5.5 (Max, Default Fallback)", "value": 57.6 }, { "rank": 2, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Claude Sonnet 5.5 (Max, Default Fallback)", "value": 56 }, { "rank": 3, "permaslug": "moonshotai/kimi-k3.1-pro-20261023", "catalog_id": "moonshotai/kimi-k3.1-pro", "name": "Kimi K3.1 Pro", "value": 55.1 }, { "rank": 4, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1 (Max, Default Fallback)", "value": 53.4 }, { "rank": 5, "permaslug": "openai/gpt-6-astra-20260903", "catalog_id": "openai/gpt-6-astra", "name": "GPT-6 Astra (Max)", "value": 52.7 }, { "rank": 6, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Gemini 4 Argon (High)", "value": 52.6 }, { "rank": 7, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol (Max)", "value": 51.8 }, { "rank": 8, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5 (Max)", "value": 50.8 }, { "rank": 9, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5 (Max, Opus 4.8 Fallback)", "value": 49.6 }, { "rank": 10, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (Max)", "value": 48.1 }, { "rank": 11, "permaslug": "openai/gpt-6.1-terra-20261026", "catalog_id": "openai/gpt-6.1-terra", "name": "GPT-6.1 Terra (Max)", "value": 48.1 }, { "rank": 12, "permaslug": "openai/gpt-6-sol-20260922", "catalog_id": "openai/gpt-6-sol", "name": "GPT-6 Sol (Max)", "value": 47.6 }, { "rank": 13, "permaslug": "openai/gpt-5.6-sol-20260709", "catalog_id": "openai/gpt-5.6-sol", "name": "GPT-5.6 Sol (Max)", "value": 47 }, { "rank": 14, "permaslug": "x-ai/grok-4.7-20260916", "catalog_id": "x-ai/grok-4.7", "name": "Grok 4.7 (Xhigh)", "value": 46.4 }, { "rank": 15, "permaslug": "xiaomi/mimo-v2.6-pro-20260921", "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "MiMo-V2.6-Pro", "value": 46.3 }, { "rank": 16, "permaslug": "qwen/qwen3.8-max-20260902", "catalog_id": "qwen/qwen3.8-max-0902", "name": "Qwen3.8 Max (0902)", "value": 45.4 }, { "rank": 17, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3 (Max)", "value": 44.8 }, { "rank": 18, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6 (High)", "value": 44.3 }, { "rank": 19, "permaslug": "stepfun/step-5-preview-20261008", "catalog_id": "stepfun/step-5-preview", "name": "Step 5 Preview", "value": 43.7 }, { "rank": 20, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3 (Max)", "value": 43.6 }, { "rank": 21, "permaslug": "anthropic/claude-haiku-5.5-20261007", "catalog_id": "anthropic/claude-haiku-5.5", "name": "Claude Haiku 5.5 (Max)", "value": 43.4 }, { "rank": 22, "permaslug": "minimax/minimax-m3.1-flash-20261019", "catalog_id": "minimax/minimax-m3.1-flash", "name": "MiniMax-M3.1-Flash", "value": 42.7 }, { "rank": 23, "permaslug": "openai/gpt-5.6-terra-20260709", "catalog_id": "openai/gpt-5.6-terra", "name": "GPT-5.6 Terra (Max)", "value": 42.1 }, { "rank": 24, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8 (Max)", "value": 41.8 }, { "rank": 25, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM-5.3-Flash", "value": 41.8 }, { "rank": 26, "permaslug": "inclusionai/ling-3.1-flash-20261002", "catalog_id": "inclusionai/ling-3.1-flash", "name": "Ling 3.1 Flash", "value": 41.1 }, { "rank": 27, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash (High)", "value": 40.9 }, { "rank": 28, "permaslug": "qwen/qwen3.8-2.4t-a95b-20260812", "catalog_id": "qwen/qwen3.8-2.4t-a95b", "name": "Qwen3.8 2.4T A95B", "value": 39.9 }, { "rank": 29, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2 (Xhigh)", "value": 39.6 }, { "rank": 30, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash (Medium)", "value": 39.6 }, { "rank": 31, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek V4.1 Flash (Max)", "value": 39.5 }, { "rank": 32, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5 (High)", "value": 38.8 }, { "rank": 33, "permaslug": "mistralai/mistral-large-4-0-20261006", "catalog_id": "mistralai/mistral-large-4-0", "name": "Mistral Large 4 Preview", "value": 38.4 }, { "rank": 34, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5 (Max)", "value": 38.2 }, { "rank": 35, "permaslug": "openai/gpt-6-luna-20260922", "catalog_id": "openai/gpt-6-luna", "name": "GPT-6 Luna (Max)", "value": 38.1 }, { "rank": 36, "permaslug": "xiaomi/mimo-v2.6-flash-20260921", "catalog_id": "xiaomi/mimo-v2.6-flash", "name": "MiMo-V2.6-Flash", "value": 37.9 }, { "rank": 37, "permaslug": "openai/gpt-5.6-luna-20260709", "catalog_id": "openai/gpt-5.6-luna", "name": "GPT-5.6 Luna (Max)", "value": 37.3 }, { "rank": 38, "permaslug": "deepseek/deepseek-v4-pro-20260813", "catalog_id": "deepseek/deepseek-v4-pro-0813", "name": "DeepSeek V4 Pro 0813 (Max)", "value": 36 }, { "rank": 39, "permaslug": "deepseek/deepseek-v4-flash-vision-exp-20260821", "catalog_id": "deepseek/deepseek-v4-flash-vision-exp", "name": "DeepSeek V4 Flash Vision (Max)", "value": 34.8 }, { "rank": 40, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek V4 Flash 0731 (Max)", "value": 34.3 }, { "rank": 41, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash (High)", "value": 34 }, { "rank": 42, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1 (Xhigh)", "value": 33.7 }, { "rank": 43, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM-5.2 (Max)", "value": 33.7 }, { "rank": 44, "permaslug": "qwen/qwen3.8-27b-20260814", "catalog_id": "qwen/qwen3.8-27b", "name": "Qwen3.8 27B (Xhigh)", "value": 33.7 }, { "rank": 45, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash (Medium)", "value": 33.6 }, { "rank": 46, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 29.5 }, { "rank": 47, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax-M3", "value": 29.2 }, { "rank": 48, "permaslug": "upstage/solar-pro4-20260810", "catalog_id": "upstage/solar-pro4", "name": "Solar Pro 4", "value": 28.2 }, { "rank": 49, "permaslug": "x-ai/grok-build-0.1-20260520", "catalog_id": "x-ai/grok-build-0.1", "name": "Grok Build 0.1 0616", "value": 27.2 }, { "rank": 50, "permaslug": "nvidia/nemotron-3.5-super-vl-20261015", "catalog_id": "nvidia/nemotron-3.5-super-vl", "name": "Nemotron 3.5 Super VL", "value": 26.5 }, { "rank": 51, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 25.8 }, { "rank": 52, "permaslug": "thinkingmachines/inkling-small-20260730", "catalog_id": "thinkingmachines/inkling-small", "name": "Inkling Small", "value": 25.7 }, { "rank": 53, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen3.7 Plus", "value": 25.2 }, { "rank": 54, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Inkling (Xhigh)", "value": 25 }, { "rank": 55, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3 (High)", "value": 24.9 }, { "rank": 56, "permaslug": "deepseek/deepseek-v4.1-flash-20260910", "catalog_id": "deepseek/deepseek-v4.1-flash", "name": "DeepSeek V4.1 Flash (Non-reasoning)", "value": 24.7 }, { "rank": 57, "permaslug": "inclusionai/ling-3.0-flash-vl-20260910", "catalog_id": "inclusionai/ling-3.0-flash-vl", "name": "Ling-3.0-flash-VL", "value": 24.6 }, { "rank": 58, "permaslug": "upstage/solar-mini4-20260922", "catalog_id": "upstage/solar-mini4", "name": "Solar Mini 4", "value": 24.1 }, { "rank": 59, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra 550B A55B (Reasoning)", "value": 22.9 }, { "rank": 60, "permaslug": "google/gemini-3.5-flash-lite-20260721", "catalog_id": "google/gemini-3.5-flash-lite", "name": "Gemini 3.5 Flash-Lite", "value": 22.2 }, { "rank": 61, "permaslug": "qwen/qwen3.6-27b-20260422", "catalog_id": "qwen/qwen3.6-27b", "name": "Qwen3.6 27B (Reasoning)", "value": 21.4 }, { "rank": 62, "permaslug": "inclusionai/ling-3.0-flash-20260723", "catalog_id": "inclusionai/ling-3.0-flash", "name": "Ling 3.0 Flash", "value": 20.1 }, { "rank": 63, "permaslug": "stepfun/step-3.7-flash-20260528", "catalog_id": "stepfun/step-3.7-flash", "name": "Step 3.7 Flash", "value": 19.5 }, { "rank": 64, "permaslug": "meituan/longcat-2.0-20260720", "catalog_id": "meituan/longcat-2.0", "name": "LongCat 2.0", "value": 19.1 }, { "rank": 65, "permaslug": "qwen/qwen3.6-35b-a3b-20260415", "catalog_id": "qwen/qwen3.6-35b-a3b", "name": "Qwen3.6 35B A3B (Reasoning)", "value": 18.2 }, { "rank": 66, "permaslug": "meta/muse-glimmer-30b-20260810", "catalog_id": "meta/muse-glimmer-30b", "name": "Muse Glimmer (High)", "value": 17.5 }, { "rank": 67, "permaslug": "mistralai/mistral-medium-3.5-20260430", "catalog_id": "mistralai/mistral-medium-3-5", "name": "Mistral Medium 3.5", "value": 14.2 }, { "rank": 68, "permaslug": "cohere/command-a-plus-05-2026", "catalog_id": "cohere/command-a-plus", "name": "Command A+", "value": 13.1 }, { "rank": 69, "permaslug": "nvidia/nemotron-3.5-lightning-20260807", "catalog_id": "nvidia/nemotron-3.5-lightning", "name": "Nemotron 3.5 Lightning", "value": 12.9 }, { "rank": 70, "permaslug": "inception/mercury-2.5-20260908", "catalog_id": "inception/mercury-2.5", "name": "Mercury 2.5", "value": 12.3 }, { "rank": 71, "permaslug": "ibm-granite/granite-4.2-8b-20260831", "catalog_id": "ibm-granite/granite-4.2-8b", "name": "Granite 4.2 8B", "value": 11.1 }, { "rank": 72, "permaslug": "liquid/lfm-2.5-2.6b-20260811", "catalog_id": "liquid/lfm-2.5-2.6b", "name": "LFM2.5-2.6B", "value": 8.4 } ], "id": "aa-intelligence", "source": "artificial-analysis", "group": "quality", "field": "intelligence_index", "direction": "higher_better", "missing_in_window": 63 }, { "ranked_count": 50, "scored_count": 50, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1 (Max, Default Fallback)", "value": 81.6 }, { "rank": 2, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5 (Max)", "value": 78 }, { "rank": 3, "permaslug": "openai/gpt-5.6-sol-20260709", "catalog_id": "openai/gpt-5.6-sol", "name": "GPT-5.6 Sol (Max)", "value": 77.4 }, { "rank": 4, "permaslug": "openai/gpt-6-astra-20260903", "catalog_id": "openai/gpt-6-astra", "name": "GPT-6 Astra (Max)", "value": 76.9 }, { "rank": 5, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6 (High)", "value": 76.8 }, { "rank": 6, "permaslug": "openai/gpt-5.6-terra-20260709", "catalog_id": "openai/gpt-5.6-terra", "name": "GPT-5.6 Terra (Max)", "value": 76.7 }, { "rank": 7, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5 (Max, Opus 4.8 Fallback)", "value": 76.5 }, { "rank": 8, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash (High)", "value": 76.3 }, { "rank": 9, "permaslug": "qwen/qwen3.8-max-20260902", "catalog_id": "qwen/qwen3.8-max-0902", "name": "Qwen3.8 Max (0902)", "value": 76.2 }, { "rank": 10, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3 (Max)", "value": 76.2 }, { "rank": 11, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (Max)", "value": 75.8 }, { "rank": 12, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3 (Max)", "value": 74.8 }, { "rank": 13, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8 (Max)", "value": 74.3 }, { "rank": 14, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5 (High)", "value": 72.4 }, { "rank": 15, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2 (Xhigh)", "value": 72.2 }, { "rank": 16, "permaslug": "qwen/qwen3.8-2.4t-a95b-20260812", "catalog_id": "qwen/qwen3.8-2.4t-a95b", "name": "Qwen3.8 2.4T A95B", "value": 71.9 }, { "rank": 17, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM-5.3-Flash", "value": 71.5 }, { "rank": 18, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash (Medium)", "value": 71.5 }, { "rank": 19, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5 (Max)", "value": 71.5 }, { "rank": 20, "permaslug": "openai/gpt-5.6-luna-20260709", "catalog_id": "openai/gpt-5.6-luna", "name": "GPT-5.6 Luna (Max)", "value": 71.4 }, { "rank": 21, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1 (Xhigh)", "value": 71.3 }, { "rank": 22, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash (High)", "value": 69.2 }, { "rank": 23, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek V4 Flash 0731 (Max)", "value": 69.1 }, { "rank": 24, "permaslug": "deepseek/deepseek-v4-pro-20260813", "catalog_id": "deepseek/deepseek-v4-pro-0813", "name": "DeepSeek V4 Pro 0813 (Max)", "value": 68.8 }, { "rank": 25, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM-5.2 (Max)", "value": 68.8 }, { "rank": 26, "permaslug": "qwen/qwen3.8-27b-20260814", "catalog_id": "qwen/qwen3.8-27b", "name": "Qwen3.8 27B (Xhigh)", "value": 68.1 }, { "rank": 27, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 66 }, { "rank": 28, "permaslug": "deepseek/deepseek-v4-flash-vision-exp-20260821", "catalog_id": "deepseek/deepseek-v4-flash-vision-exp", "name": "DeepSeek V4 Flash Vision (Max)", "value": 65 }, { "rank": 29, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 60.8 }, { "rank": 30, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax-M3", "value": 58.6 }, { "rank": 31, "permaslug": "inclusionai/ling-3.0-flash-vl-20260910", "catalog_id": "inclusionai/ling-3.0-flash-vl", "name": "Ling-3.0-flash-VL", "value": 57 }, { "rank": 32, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen3.7 Plus", "value": 55.9 }, { "rank": 33, "permaslug": "qwen/qwen3.6-27b-20260422", "catalog_id": "qwen/qwen3.6-27b", "name": "Qwen3.6 27B (Reasoning)", "value": 53.7 }, { "rank": 34, "permaslug": "thinkingmachines/inkling-small-20260730", "catalog_id": "thinkingmachines/inkling-small", "name": "Inkling Small", "value": 52.9 }, { "rank": 35, "permaslug": "upstage/solar-pro4-20260810", "catalog_id": "upstage/solar-pro4", "name": "Solar Pro 4", "value": 52.7 }, { "rank": 36, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Inkling (Xhigh)", "value": 52.1 }, { "rank": 37, "permaslug": "x-ai/grok-build-0.1-20260520", "catalog_id": "x-ai/grok-build-0.1", "name": "Grok Build 0.1 0616", "value": 51.5 }, { "rank": 38, "permaslug": "inclusionai/ling-3.0-flash-20260723", "catalog_id": "inclusionai/ling-3.0-flash", "name": "Ling 3.0 Flash", "value": 50.6 }, { "rank": 39, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra 550B A55B (Reasoning)", "value": 49.3 }, { "rank": 40, "permaslug": "google/gemini-3.5-flash-lite-20260721", "catalog_id": "google/gemini-3.5-flash-lite", "name": "Gemini 3.5 Flash-Lite", "value": 49.3 }, { "rank": 41, "permaslug": "meta/muse-glimmer-30b-20260810", "catalog_id": "meta/muse-glimmer-30b", "name": "Muse Glimmer (High)", "value": 49 }, { "rank": 42, "permaslug": "mistralai/mistral-medium-3.5-20260430", "catalog_id": "mistralai/mistral-medium-3-5", "name": "Mistral Medium 3.5", "value": 46.9 }, { "rank": 43, "permaslug": "meituan/longcat-2.0-20260720", "catalog_id": "meituan/longcat-2.0", "name": "LongCat 2.0", "value": 45.3 }, { "rank": 44, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3 (High)", "value": 42.2 }, { "rank": 45, "permaslug": "qwen/qwen3.6-35b-a3b-20260415", "catalog_id": "qwen/qwen3.6-35b-a3b", "name": "Qwen3.6 35B A3B (Reasoning)", "value": 41.9 }, { "rank": 46, "permaslug": "stepfun/step-3.7-flash-20260528", "catalog_id": "stepfun/step-3.7-flash", "name": "Step 3.7 Flash", "value": 39.6 }, { "rank": 47, "permaslug": "cohere/command-a-plus-05-2026", "catalog_id": "cohere/command-a-plus", "name": "Command A+", "value": 27.8 }, { "rank": 48, "permaslug": "nvidia/nemotron-3.5-lightning-20260807", "catalog_id": "nvidia/nemotron-3.5-lightning", "name": "Nemotron 3.5 Lightning", "value": 26.8 }, { "rank": 49, "permaslug": "ibm-granite/granite-4.2-8b-20260831", "catalog_id": "ibm-granite/granite-4.2-8b", "name": "Granite 4.2 8B", "value": 22.4 }, { "rank": 50, "permaslug": "liquid/lfm-2.5-2.6b-20260811", "catalog_id": "liquid/lfm-2.5-2.6b", "name": "LFM2.5-2.6B", "value": 7.7 } ], "id": "aa-coding", "source": "artificial-analysis", "group": "quality", "field": "coding_index", "direction": "higher_better", "missing_in_window": 85 }, { "ranked_count": 45, "scored_count": 45, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1 (Max, Default Fallback)", "value": 57.9 }, { "rank": 2, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5 (Max)", "value": 56.5 }, { "rank": 3, "permaslug": "qwen/qwen3.8-max-20260902", "catalog_id": "qwen/qwen3.8-max-0902", "name": "Qwen3.8 Max (0902)", "value": 56 }, { "rank": 4, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (Max)", "value": 55.5 }, { "rank": 5, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3 (Max)", "value": 53.1 }, { "rank": 6, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6 (High)", "value": 53 }, { "rank": 7, "permaslug": "openai/gpt-6-astra-20260903", "catalog_id": "openai/gpt-6-astra", "name": "GPT-6 Astra (Max)", "value": 51 }, { "rank": 8, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM-5.3-Flash", "value": 50.9 }, { "rank": 9, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5 (Max, Opus 4.8 Fallback)", "value": 50.7 }, { "rank": 10, "permaslug": "openai/gpt-5.6-sol-20260709", "catalog_id": "openai/gpt-5.6-sol", "name": "GPT-5.6 Sol (Max)", "value": 50.2 }, { "rank": 11, "permaslug": "qwen/qwen3.8-2.4t-a95b-20260812", "catalog_id": "qwen/qwen3.8-2.4t-a95b", "name": "Qwen3.8 2.4T A95B", "value": 50.1 }, { "rank": 12, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3 (Max)", "value": 50 }, { "rank": 13, "permaslug": "deepseek/deepseek-v4-flash-vision-exp-20260821", "catalog_id": "deepseek/deepseek-v4-flash-vision-exp", "name": "DeepSeek V4 Flash Vision (Max)", "value": 47.5 }, { "rank": 14, "permaslug": "qwen/qwen3.8-27b-20260814", "catalog_id": "qwen/qwen3.8-27b", "name": "Qwen3.8 27B (Xhigh)", "value": 45.8 }, { "rank": 15, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5 (Max)", "value": 43.6 }, { "rank": 16, "permaslug": "openai/gpt-5.6-terra-20260709", "catalog_id": "openai/gpt-5.6-terra", "name": "GPT-5.6 Terra (Max)", "value": 43.2 }, { "rank": 17, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2 (Xhigh)", "value": 43.2 }, { "rank": 18, "permaslug": "openai/gpt-5.6-luna-20260709", "catalog_id": "openai/gpt-5.6-luna", "name": "GPT-5.6 Luna (Max)", "value": 42.1 }, { "rank": 19, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8 (Max)", "value": 41.9 }, { "rank": 20, "permaslug": "deepseek/deepseek-v4-pro-20260813", "catalog_id": "deepseek/deepseek-v4-pro-0813", "name": "DeepSeek V4 Pro 0813 (Max)", "value": 41.3 }, { "rank": 21, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5 (High)", "value": 41.2 }, { "rank": 22, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek V4 Flash 0731 (Max)", "value": 41 }, { "rank": 23, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash (High)", "value": 40.2 }, { "rank": 24, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM-5.2 (Max)", "value": 38.4 }, { "rank": 25, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax-M3", "value": 29.5 }, { "rank": 26, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash (High)", "value": 29 }, { "rank": 27, "permaslug": "inclusionai/ling-3.0-flash-vl-20260910", "catalog_id": "inclusionai/ling-3.0-flash-vl", "name": "Ling-3.0-flash-VL", "value": 28.7 }, { "rank": 28, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1 (Xhigh)", "value": 25.8 }, { "rank": 29, "permaslug": "thinkingmachines/inkling-small-20260730", "catalog_id": "thinkingmachines/inkling-small", "name": "Inkling Small", "value": 23.5 }, { "rank": 30, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 22.5 }, { "rank": 31, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Inkling (Xhigh)", "value": 22.5 }, { "rank": 32, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 21 }, { "rank": 33, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra 550B A55B (Reasoning)", "value": 20.1 }, { "rank": 34, "permaslug": "inclusionai/ling-3.0-flash-20260723", "catalog_id": "inclusionai/ling-3.0-flash", "name": "Ling 3.0 Flash", "value": 19.3 }, { "rank": 35, "permaslug": "qwen/qwen3.6-27b-20260422", "catalog_id": "qwen/qwen3.6-27b", "name": "Qwen3.6 27B (Reasoning)", "value": 18.5 }, { "rank": 36, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen3.7 Plus", "value": 17.5 }, { "rank": 37, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3 (High)", "value": 15.5 }, { "rank": 38, "permaslug": "google/gemini-3.5-flash-lite-20260721", "catalog_id": "google/gemini-3.5-flash-lite", "name": "Gemini 3.5 Flash-Lite", "value": 14.3 }, { "rank": 39, "permaslug": "meituan/longcat-2.0-20260720", "catalog_id": "meituan/longcat-2.0", "name": "LongCat 2.0", "value": 14 }, { "rank": 40, "permaslug": "qwen/qwen3.6-35b-a3b-20260415", "catalog_id": "qwen/qwen3.6-35b-a3b", "name": "Qwen3.6 35B A3B (Reasoning)", "value": 13.1 }, { "rank": 41, "permaslug": "meta/muse-glimmer-30b-20260810", "catalog_id": "meta/muse-glimmer-30b", "name": "Muse Glimmer (High)", "value": 8.5 }, { "rank": 42, "permaslug": "mistralai/mistral-medium-3.5-20260430", "catalog_id": "mistralai/mistral-medium-3-5", "name": "Mistral Medium 3.5", "value": 7 }, { "rank": 43, "permaslug": "nvidia/nemotron-3.5-lightning-20260807", "catalog_id": "nvidia/nemotron-3.5-lightning", "name": "Nemotron 3.5 Lightning", "value": 3.5 }, { "rank": 44, "permaslug": "ibm-granite/granite-4.2-8b-20260831", "catalog_id": "ibm-granite/granite-4.2-8b", "name": "Granite 4.2 8B", "value": 1.3 }, { "rank": 45, "permaslug": "cohere/command-a-plus-05-2026", "catalog_id": "cohere/command-a-plus", "name": "Command A+", "value": 1 } ], "id": "aa-agentic", "source": "artificial-analysis", "group": "quality", "field": "agentic_index", "direction": "higher_better", "missing_in_window": 90 }, { "ranked_count": 43, "scored_count": 43, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Claude Opus 5.5", "value": 1468, "win_rate": 65 }, { "rank": 2, "permaslug": "moonshotai/kimi-k3.1-pro-20261023", "catalog_id": "moonshotai/kimi-k3.1-pro", "name": "Kimi K3.1 Pro", "value": 1448, "win_rate": 72.5 }, { "rank": 3, "permaslug": "meta/muse-wonder-20261012", "catalog_id": "meta/muse-wonder", "name": "Muse Wonder (max)", "value": 1446, "win_rate": 62 }, { "rank": 4, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "value": 1436, "win_rate": 59.6 }, { "rank": 5, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Claude Sonnet 5.5", "value": 1401, "win_rate": 51.4 }, { "rank": 6, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 Max", "value": 1393, "win_rate": 63.5 }, { "rank": 7, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 1390, "win_rate": 67.7 }, { "rank": 8, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Gemini 4 Argon", "value": 1385, "win_rate": 55.7 }, { "rank": 9, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 1385, "win_rate": 67.2 }, { "rank": 10, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek-V4.1-Flash (1017)", "value": 1362, "win_rate": 46.7 }, { "rank": 11, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 1361, "win_rate": 56.5 }, { "rank": 12, "permaslug": "anthropic/claude-haiku-5.5-20261007", "catalog_id": "anthropic/claude-haiku-5.5", "name": "Claude Haiku 5.5", "value": 1344, "win_rate": 58.2 }, { "rank": 13, "permaslug": "xiaomi/mimo-v2.6-pro-20260921", "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "MiMo-V2.6-Pro", "value": 1333, "win_rate": 57.5 }, { "rank": 14, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 1332, "win_rate": 59.7 }, { "rank": 15, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3", "value": 1329, "win_rate": 59.2 }, { "rank": 16, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 1316, "win_rate": 61.8 }, { "rank": 17, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM-5.3-Flash", "value": 1314, "win_rate": 56.2 }, { "rank": 18, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 1306, "win_rate": 53.9 }, { "rank": 19, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 1300, "win_rate": 51.8 }, { "rank": 20, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 1293, "win_rate": 49.9 }, { "rank": 21, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 1284, "win_rate": 53 }, { "rank": 22, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 1273, "win_rate": 52.3 }, { "rank": 23, "permaslug": "x-ai/grok-4.7-20260916", "catalog_id": "x-ai/grok-4.7", "name": "Grok 4.7", "value": 1273, "win_rate": 48.4 }, { "rank": 24, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 1269, "win_rate": 52.9 }, { "rank": 25, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 1263, "win_rate": 54.3 }, { "rank": 26, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 1258, "win_rate": 53.9 }, { "rank": 27, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 1258, "win_rate": 49 }, { "rank": 28, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 1255, "win_rate": 50.2 }, { "rank": 29, "permaslug": "mistralai/mistral-large-4-0-20261006", "catalog_id": "mistralai/mistral-large-4-0", "name": "Mistral Large 4", "value": 1248, "win_rate": 45 }, { "rank": 30, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1240, "win_rate": 55.8 }, { "rank": 31, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 1238, "win_rate": 50.3 }, { "rank": 32, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen3.7 Plus", "value": 1236, "win_rate": 48.4 }, { "rank": 33, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1220, "win_rate": 51.2 }, { "rank": 34, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek-V4-Flash-0731", "value": 1206, "win_rate": 48.7 }, { "rank": 35, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 1206, "win_rate": 50.1 }, { "rank": 36, "permaslug": "upstage/solar-pro4-20260810", "catalog_id": "upstage/solar-pro4", "name": "Solar Pro 4", "value": 1175, "win_rate": 46.4 }, { "rank": 37, "permaslug": "tencent/hy3-20260706", "catalog_id": "tencent/hy3", "name": "Hy3 Low", "value": 1173, "win_rate": 44 }, { "rank": 38, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Inkling", "value": 1156, "win_rate": 39.9 }, { "rank": 39, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra", "value": 1127, "win_rate": 38.1 }, { "rank": 40, "permaslug": "stepfun/step-3.7-flash-20260528", "catalog_id": "stepfun/step-3.7-flash", "name": "Step 3.7 Flash", "value": 1126, "win_rate": 39.9 }, { "rank": 41, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 1122, "win_rate": 40.8 }, { "rank": 42, "permaslug": "nvidia/nemotron-3.5-super-vl-20261015", "catalog_id": "nvidia/nemotron-3.5-super-vl", "name": "Nemotron 3.5 Super VL", "value": 1116, "win_rate": 28.1 }, { "rank": 43, "permaslug": "upstage/solar-mini4-20260922", "catalog_id": "upstage/solar-mini4", "name": "Solar Mini 4", "value": 1081, "win_rate": 21.7 } ], "id": "da-models-3d", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 93 }, { "ranked_count": 43, "scored_count": 43, "truncated": false, "rows": [ { "rank": 1, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 45818, "win_rate": 40.8 }, { "rank": 2, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 64698, "win_rate": 52.9 }, { "rank": 3, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 70339, "win_rate": 55.8 }, { "rank": 4, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Inkling", "value": 75177, "win_rate": 39.9 }, { "rank": 5, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 79658, "win_rate": 49.9 }, { "rank": 6, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 82319, "win_rate": 53.9 }, { "rank": 7, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 87889, "win_rate": 51.2 }, { "rank": 8, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 96442, "win_rate": 50.1 }, { "rank": 9, "permaslug": "nvidia/nemotron-3.5-super-vl-20261015", "catalog_id": "nvidia/nemotron-3.5-super-vl", "name": "Nemotron 3.5 Super VL", "value": 97170, "win_rate": 28.1 }, { "rank": 10, "permaslug": "stepfun/step-3.7-flash-20260528", "catalog_id": "stepfun/step-3.7-flash", "name": "Step 3.7 Flash", "value": 103744, "win_rate": 39.9 }, { "rank": 11, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra", "value": 110486, "win_rate": 38.1 }, { "rank": 12, "permaslug": "tencent/hy3-20260706", "catalog_id": "tencent/hy3", "name": "Hy3 Low", "value": 120415, "win_rate": 44 }, { "rank": 13, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 123978, "win_rate": 50.2 }, { "rank": 14, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 135284, "win_rate": 61.8 }, { "rank": 15, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Gemini 4 Argon", "value": 140429, "win_rate": 55.7 }, { "rank": 16, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 156166, "win_rate": 56.5 }, { "rank": 17, "permaslug": "anthropic/claude-haiku-5.5-20261007", "catalog_id": "anthropic/claude-haiku-5.5", "name": "Claude Haiku 5.5", "value": 163877, "win_rate": 58.2 }, { "rank": 18, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen3.7 Plus", "value": 173377, "win_rate": 48.4 }, { "rank": 19, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 177067, "win_rate": 54.3 }, { "rank": 20, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 186887, "win_rate": 49 }, { "rank": 21, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 187715, "win_rate": 51.8 }, { "rank": 22, "permaslug": "upstage/solar-mini4-20260922", "catalog_id": "upstage/solar-mini4", "name": "Solar Mini 4", "value": 199272, "win_rate": 21.7 }, { "rank": 23, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "value": 203339, "win_rate": 59.6 }, { "rank": 24, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 220898, "win_rate": 53.9 }, { "rank": 25, "permaslug": "meta/muse-wonder-20261012", "catalog_id": "meta/muse-wonder", "name": "Muse Wonder (max)", "value": 230553, "win_rate": 62 }, { "rank": 26, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 232648, "win_rate": 52.3 }, { "rank": 27, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 Max", "value": 236247, "win_rate": 63.5 }, { "rank": 28, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 248004, "win_rate": 50.3 }, { "rank": 29, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek-V4-Flash-0731", "value": 254333, "win_rate": 48.7 }, { "rank": 30, "permaslug": "upstage/solar-pro4-20260810", "catalog_id": "upstage/solar-pro4", "name": "Solar Pro 4", "value": 259568, "win_rate": 46.4 }, { "rank": 31, "permaslug": "xiaomi/mimo-v2.6-pro-20260921", "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "MiMo-V2.6-Pro", "value": 277661, "win_rate": 57.5 }, { "rank": 32, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 304684, "win_rate": 67.7 }, { "rank": 33, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 331748, "win_rate": 59.7 }, { "rank": 34, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 345940, "win_rate": 53 }, { "rank": 35, "permaslug": "mistralai/mistral-large-4-0-20261006", "catalog_id": "mistralai/mistral-large-4-0", "name": "Mistral Large 4", "value": 385636, "win_rate": 45 }, { "rank": 36, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek-V4.1-Flash (1017)", "value": 392585, "win_rate": 46.7 }, { "rank": 37, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Claude Opus 5.5", "value": 398521, "win_rate": 65 }, { "rank": 38, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3", "value": 476086, "win_rate": 59.2 }, { "rank": 39, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM-5.3-Flash", "value": 524587, "win_rate": 56.2 }, { "rank": 40, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Claude Sonnet 5.5", "value": 578825, "win_rate": 51.4 }, { "rank": 41, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 649929, "win_rate": 67.2 }, { "rank": 42, "permaslug": "x-ai/grok-4.7-20260916", "catalog_id": "x-ai/grok-4.7", "name": "Grok 4.7", "value": 861386, "win_rate": 48.4 }, { "rank": 43, "permaslug": "moonshotai/kimi-k3.1-pro-20261023", "catalog_id": "moonshotai/kimi-k3.1-pro", "name": "Kimi K3.1 Pro", "value": 1112671, "win_rate": 72.5 } ], "id": "da-models-3d-speed", "source": "design-arena", "group": "speed", "field": "avg_generation_time_ms", "direction": "lower_better", "missing_in_window": 93 }, { "ranked_count": 28, "scored_count": 28, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 1358, "win_rate": 68.6 }, { "rank": 2, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 1326, "win_rate": 68.1 }, { "rank": 3, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 1321, "win_rate": 65 }, { "rank": 4, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 1280, "win_rate": 55.5 }, { "rank": 5, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 1279, "win_rate": 58.5 }, { "rank": 6, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 1278, "win_rate": 53.4 }, { "rank": 7, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 1277, "win_rate": 57.1 }, { "rank": 8, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 1277, "win_rate": 55.6 }, { "rank": 9, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1275, "win_rate": 62.3 }, { "rank": 10, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM-5.3-Flash", "value": 1271, "win_rate": 55.2 }, { "rank": 11, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 1267, "win_rate": 52.1 }, { "rank": 12, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 1261, "win_rate": 53.5 }, { "rank": 13, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 1257, "win_rate": 54.5 }, { "rank": 14, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1250, "win_rate": 58.8 }, { "rank": 15, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek-V4.1-Flash (1017)", "value": 1220, "win_rate": 50.8 }, { "rank": 16, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 1209, "win_rate": 53.2 }, { "rank": 17, "permaslug": "mistralai/mistral-large-4-0-20261006", "catalog_id": "mistralai/mistral-large-4-0", "name": "Mistral Large 4", "value": 1206, "win_rate": 43.5 }, { "rank": 18, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 1205, "win_rate": 51.3 }, { "rank": 19, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3", "value": 1205, "win_rate": 47.1 }, { "rank": 20, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 1193, "win_rate": 48.3 }, { "rank": 21, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 1188, "win_rate": 46.2 }, { "rank": 22, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 1158, "win_rate": 46.3 }, { "rank": 23, "permaslug": "stepfun/step-3.7-flash-20260528", "catalog_id": "stepfun/step-3.7-flash", "name": "Step 3.7 Flash", "value": 1150, "win_rate": 45 }, { "rank": 24, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen3.7 Plus", "value": 1138, "win_rate": 40.8 }, { "rank": 25, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 1122, "win_rate": 42.3 }, { "rank": 26, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra", "value": 1098, "win_rate": 37.3 }, { "rank": 27, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek-V4-Flash-0731", "value": 1088, "win_rate": 33.3 }, { "rank": 28, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Inkling", "value": 1087, "win_rate": 33.6 } ], "id": "da-models-asciiart", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 107 }, { "ranked_count": 28, "scored_count": 28, "truncated": false, "rows": [ { "rank": 1, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 27370, "win_rate": 42.3 }, { "rank": 2, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 28498, "win_rate": 62.3 }, { "rank": 3, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 48819, "win_rate": 55.6 }, { "rank": 4, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 56072, "win_rate": 54.5 }, { "rank": 5, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 57036, "win_rate": 52.1 }, { "rank": 6, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 58933, "win_rate": 57.1 }, { "rank": 7, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 64357, "win_rate": 51.3 }, { "rank": 8, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 71835, "win_rate": 46.3 }, { "rank": 9, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 84776, "win_rate": 58.8 }, { "rank": 10, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 86119, "win_rate": 68.1 }, { "rank": 11, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Inkling", "value": 96682, "win_rate": 33.6 }, { "rank": 12, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra", "value": 104820, "win_rate": 37.3 }, { "rank": 13, "permaslug": "stepfun/step-3.7-flash-20260528", "catalog_id": "stepfun/step-3.7-flash", "name": "Step 3.7 Flash", "value": 109891, "win_rate": 45 }, { "rank": 14, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 136224, "win_rate": 53.4 }, { "rank": 15, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 141979, "win_rate": 53.5 }, { "rank": 16, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 170349, "win_rate": 58.5 }, { "rank": 17, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 173399, "win_rate": 55.5 }, { "rank": 18, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 188435, "win_rate": 65 }, { "rank": 19, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek-V4.1-Flash (1017)", "value": 189868, "win_rate": 50.8 }, { "rank": 20, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen3.7 Plus", "value": 238782, "win_rate": 40.8 }, { "rank": 21, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 250062, "win_rate": 68.6 }, { "rank": 22, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 254766, "win_rate": 53.2 }, { "rank": 23, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 285531, "win_rate": 46.2 }, { "rank": 24, "permaslug": "mistralai/mistral-large-4-0-20261006", "catalog_id": "mistralai/mistral-large-4-0", "name": "Mistral Large 4", "value": 294200, "win_rate": 43.5 }, { "rank": 25, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek-V4-Flash-0731", "value": 320360, "win_rate": 33.3 }, { "rank": 26, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 322333, "win_rate": 48.3 }, { "rank": 27, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM-5.3-Flash", "value": 427804, "win_rate": 55.2 }, { "rank": 28, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3", "value": 448291, "win_rate": 47.1 } ], "id": "da-models-asciiart-speed", "source": "design-arena", "group": "speed", "field": "avg_generation_time_ms", "direction": "lower_better", "missing_in_window": 107 }, { "ranked_count": 46, "scored_count": 46, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Claude Opus 5.5", "value": 1386, "win_rate": 61.5 }, { "rank": 2, "permaslug": "meta/muse-wonder-20261012", "catalog_id": "meta/muse-wonder", "name": "Muse Wonder (max)", "value": 1383, "win_rate": 62.4 }, { "rank": 3, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 1359, "win_rate": 62.3 }, { "rank": 4, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "value": 1358, "win_rate": 57 }, { "rank": 5, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Claude Sonnet 5.5", "value": 1353, "win_rate": 56.3 }, { "rank": 6, "permaslug": "moonshotai/kimi-k3.1-pro-20261023", "catalog_id": "moonshotai/kimi-k3.1-pro", "name": "Kimi K3.1 Pro", "value": 1353, "win_rate": 60.9 }, { "rank": 7, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 1350, "win_rate": 57 }, { "rank": 8, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 Max", "value": 1349, "win_rate": 56.8 }, { "rank": 9, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 1335, "win_rate": 59.3 }, { "rank": 10, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Gemini 4 Argon", "value": 1330, "win_rate": 56.1 }, { "rank": 11, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 1323, "win_rate": 57.4 }, { "rank": 12, "permaslug": "xiaomi/mimo-v2.6-pro-20260921", "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "MiMo-V2.6-Pro", "value": 1316, "win_rate": 52.7 }, { "rank": 13, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 1311, "win_rate": 52.1 }, { "rank": 14, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 1308, "win_rate": 57.6 }, { "rank": 15, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 1306, "win_rate": 53.9 }, { "rank": 16, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 1302, "win_rate": 50.4 }, { "rank": 17, "permaslug": "meta/muse-spark-open-20261015", "catalog_id": "meta/muse-spark-open", "name": "Muse Spark Open (xhigh)", "value": 1301, "win_rate": 53.9 }, { "rank": 18, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3", "value": 1300, "win_rate": 53.8 }, { "rank": 19, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 1290, "win_rate": 52.5 }, { "rank": 20, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek-V4.1-Flash (1017)", "value": 1289, "win_rate": 47.8 }, { "rank": 21, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 1288, "win_rate": 53.4 }, { "rank": 22, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 1285, "win_rate": 50.3 }, { "rank": 23, "permaslug": "anthropic/claude-haiku-5.5-20261007", "catalog_id": "anthropic/claude-haiku-5.5", "name": "Claude Haiku 5.5", "value": 1280, "win_rate": 50.6 }, { "rank": 24, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM-5.3-Flash", "value": 1279, "win_rate": 49.2 }, { "rank": 25, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 1274, "win_rate": 52.5 }, { "rank": 26, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 1274, "win_rate": 51.2 }, { "rank": 27, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 1273, "win_rate": 53.9 }, { "rank": 28, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 1273, "win_rate": 50.8 }, { "rank": 29, "permaslug": "x-ai/grok-4.7-20260916", "catalog_id": "x-ai/grok-4.7", "name": "Grok 4.7", "value": 1271, "win_rate": 47.9 }, { "rank": 30, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen3.7 Plus", "value": 1267, "win_rate": 50.1 }, { "rank": 31, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1264, "win_rate": 54 }, { "rank": 32, "permaslug": "mistralai/mistral-large-4-0-20261006", "catalog_id": "mistralai/mistral-large-4-0", "name": "Mistral Large 4", "value": 1258, "win_rate": 46.7 }, { "rank": 33, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1253, "win_rate": 52.3 }, { "rank": 34, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 1251, "win_rate": 49.8 }, { "rank": 35, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 1245, "win_rate": 50.7 }, { "rank": 36, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek-V4-Flash-0731", "value": 1228, "win_rate": 46.4 }, { "rank": 37, "permaslug": "inception/mercury-3-20261019", "catalog_id": "inception/mercury-3", "name": "Mercury 3", "value": 1228, "win_rate": 45.2 }, { "rank": 38, "permaslug": "reflection/beam-1.0-501b-a23b-20261016", "catalog_id": "reflection/beam-1.0-501b-a23b", "name": "Beam 1.0 (max)", "value": 1222, "win_rate": 42.8 }, { "rank": 39, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Inkling", "value": 1204, "win_rate": 42.2 }, { "rank": 40, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 1185, "win_rate": 43.6 }, { "rank": 41, "permaslug": "upstage/solar-pro4-20260810", "catalog_id": "upstage/solar-pro4", "name": "Solar Pro 4", "value": 1180, "win_rate": 39 }, { "rank": 42, "permaslug": "stepfun/step-3.7-flash-20260528", "catalog_id": "stepfun/step-3.7-flash", "name": "Step 3.7 Flash", "value": 1180, "win_rate": 42 }, { "rank": 43, "permaslug": "tencent/hy3-20260706", "catalog_id": "tencent/hy3", "name": "Hy3 Low", "value": 1175, "win_rate": 41.2 }, { "rank": 44, "permaslug": "nvidia/nemotron-3.5-super-vl-20261015", "catalog_id": "nvidia/nemotron-3.5-super-vl", "name": "Nemotron 3.5 Super VL", "value": 1151, "win_rate": 32.7 }, { "rank": 45, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra", "value": 1145, "win_rate": 36 }, { "rank": 46, "permaslug": "upstage/solar-mini4-20260922", "catalog_id": "upstage/solar-mini4", "name": "Solar Mini 4", "value": 1140, "win_rate": 30.7 } ], "id": "da-models-codecategories", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 90 }, { "ranked_count": 46, "scored_count": 46, "truncated": false, "rows": [ { "rank": 1, "permaslug": "inception/mercury-3-20261019", "catalog_id": "inception/mercury-3", "name": "Mercury 3", "value": 60940, "win_rate": 45.2 }, { "rank": 2, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 66843, "win_rate": 43.6 }, { "rank": 3, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 78778, "win_rate": 53.4 }, { "rank": 4, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 85964, "win_rate": 54 }, { "rank": 5, "permaslug": "reflection/beam-1.0-501b-a23b-20261016", "catalog_id": "reflection/beam-1.0-501b-a23b", "name": "Beam 1.0 (max)", "value": 98746, "win_rate": 42.8 }, { "rank": 6, "permaslug": "nvidia/nemotron-3.5-super-vl-20261015", "catalog_id": "nvidia/nemotron-3.5-super-vl", "name": "Nemotron 3.5 Super VL", "value": 107576, "win_rate": 32.7 }, { "rank": 7, "permaslug": "stepfun/step-3.7-flash-20260528", "catalog_id": "stepfun/step-3.7-flash", "name": "Step 3.7 Flash", "value": 118610, "win_rate": 42 }, { "rank": 8, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 118616, "win_rate": 52.3 }, { "rank": 9, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 123310, "win_rate": 50.4 }, { "rank": 10, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 128522, "win_rate": 53.9 }, { "rank": 11, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Inkling", "value": 130810, "win_rate": 42.2 }, { "rank": 12, "permaslug": "tencent/hy3-20260706", "catalog_id": "tencent/hy3", "name": "Hy3 Low", "value": 132343, "win_rate": 41.2 }, { "rank": 13, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra", "value": 135595, "win_rate": 36 }, { "rank": 14, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 146591, "win_rate": 50.7 }, { "rank": 15, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 166521, "win_rate": 57.6 }, { "rank": 16, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 174130, "win_rate": 52.1 }, { "rank": 17, "permaslug": "anthropic/claude-haiku-5.5-20261007", "catalog_id": "anthropic/claude-haiku-5.5", "name": "Claude Haiku 5.5", "value": 183408, "win_rate": 50.6 }, { "rank": 18, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 186237, "win_rate": 50.8 }, { "rank": 19, "permaslug": "meta/muse-wonder-20261012", "catalog_id": "meta/muse-wonder", "name": "Muse Wonder (max)", "value": 187429, "win_rate": 62.4 }, { "rank": 20, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 192625, "win_rate": 57 }, { "rank": 21, "permaslug": "meta/muse-spark-open-20261015", "catalog_id": "meta/muse-spark-open", "name": "Muse Spark Open (xhigh)", "value": 199972, "win_rate": 53.9 }, { "rank": 22, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 200680, "win_rate": 51.2 }, { "rank": 23, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 210773, "win_rate": 52.5 }, { "rank": 24, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Gemini 4 Argon", "value": 218408, "win_rate": 56.1 }, { "rank": 25, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek-V4.1-Flash (1017)", "value": 234839, "win_rate": 47.8 }, { "rank": 26, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 237520, "win_rate": 53.9 }, { "rank": 27, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 249376, "win_rate": 50.3 }, { "rank": 28, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek-V4-Flash-0731", "value": 249794, "win_rate": 46.4 }, { "rank": 29, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 Max", "value": 254812, "win_rate": 56.8 }, { "rank": 30, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "value": 257241, "win_rate": 57 }, { "rank": 31, "permaslug": "upstage/solar-mini4-20260922", "catalog_id": "upstage/solar-mini4", "name": "Solar Mini 4", "value": 271802, "win_rate": 30.7 }, { "rank": 32, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen3.7 Plus", "value": 278884, "win_rate": 50.1 }, { "rank": 33, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 280416, "win_rate": 52.5 }, { "rank": 34, "permaslug": "upstage/solar-pro4-20260810", "catalog_id": "upstage/solar-pro4", "name": "Solar Pro 4", "value": 287680, "win_rate": 39 }, { "rank": 35, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 296436, "win_rate": 49.8 }, { "rank": 36, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 319781, "win_rate": 57.4 }, { "rank": 37, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 323413, "win_rate": 59.3 }, { "rank": 38, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Claude Opus 5.5", "value": 356567, "win_rate": 61.5 }, { "rank": 39, "permaslug": "mistralai/mistral-large-4-0-20261006", "catalog_id": "mistralai/mistral-large-4-0", "name": "Mistral Large 4", "value": 382027, "win_rate": 46.7 }, { "rank": 40, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Claude Sonnet 5.5", "value": 392218, "win_rate": 56.3 }, { "rank": 41, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3", "value": 397159, "win_rate": 53.8 }, { "rank": 42, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM-5.3-Flash", "value": 410724, "win_rate": 49.2 }, { "rank": 43, "permaslug": "xiaomi/mimo-v2.6-pro-20260921", "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "MiMo-V2.6-Pro", "value": 412933, "win_rate": 52.7 }, { "rank": 44, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 782878, "win_rate": 62.3 }, { "rank": 45, "permaslug": "x-ai/grok-4.7-20260916", "catalog_id": "x-ai/grok-4.7", "name": "Grok 4.7", "value": 803317, "win_rate": 47.9 }, { "rank": 46, "permaslug": "moonshotai/kimi-k3.1-pro-20261023", "catalog_id": "moonshotai/kimi-k3.1-pro", "name": "Kimi K3.1 Pro", "value": 1188421, "win_rate": 60.9 } ], "id": "da-models-codecategories-speed", "source": "design-arena", "group": "speed", "field": "avg_generation_time_ms", "direction": "lower_better", "missing_in_window": 90 }, { "ranked_count": 42, "scored_count": 42, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Claude Opus 5.5", "value": 1396, "win_rate": 64.8 }, { "rank": 2, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Claude Sonnet 5.5", "value": 1387, "win_rate": 67.7 }, { "rank": 3, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 1350, "win_rate": 63.2 }, { "rank": 4, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 1344, "win_rate": 61.8 }, { "rank": 5, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 1342, "win_rate": 58 }, { "rank": 6, "permaslug": "xiaomi/mimo-v2.6-pro-20260921", "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "MiMo-V2.6-Pro", "value": 1336, "win_rate": 58.8 }, { "rank": 7, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 1333, "win_rate": 57.7 }, { "rank": 8, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Gemini 4 Argon", "value": 1331, "win_rate": 61.5 }, { "rank": 9, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 1330, "win_rate": 58.5 }, { "rank": 10, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 1316, "win_rate": 55.4 }, { "rank": 11, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 Max", "value": 1307, "win_rate": 52.2 }, { "rank": 12, "permaslug": "meta/muse-wonder-20261012", "catalog_id": "meta/muse-wonder", "name": "Muse Wonder (max)", "value": 1307, "win_rate": 55.7 }, { "rank": 13, "permaslug": "moonshotai/kimi-k3.1-pro-20261023", "catalog_id": "moonshotai/kimi-k3.1-pro", "name": "Kimi K3.1 Pro", "value": 1305, "win_rate": 56.3 }, { "rank": 14, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 1304, "win_rate": 57.5 }, { "rank": 15, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "value": 1292, "win_rate": 53.7 }, { "rank": 16, "permaslug": "anthropic/claude-haiku-5.5-20261007", "catalog_id": "anthropic/claude-haiku-5.5", "name": "Claude Haiku 5.5", "value": 1291, "win_rate": 54.3 }, { "rank": 17, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 1289, "win_rate": 52.3 }, { "rank": 18, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 1285, "win_rate": 52 }, { "rank": 19, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 1282, "win_rate": 51.4 }, { "rank": 20, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen3.7 Plus", "value": 1279, "win_rate": 51.4 }, { "rank": 21, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek-V4.1-Flash (1017)", "value": 1278, "win_rate": 51.6 }, { "rank": 22, "permaslug": "mistralai/mistral-large-4-0-20261006", "catalog_id": "mistralai/mistral-large-4-0", "name": "Mistral Large 4", "value": 1275, "win_rate": 51 }, { "rank": 23, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 1275, "win_rate": 52.9 }, { "rank": 24, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 1271, "win_rate": 51.3 }, { "rank": 25, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 1267, "win_rate": 50.2 }, { "rank": 26, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 1266, "win_rate": 49.7 }, { "rank": 27, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3", "value": 1263, "win_rate": 52 }, { "rank": 28, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM-5.3-Flash", "value": 1261, "win_rate": 50.3 }, { "rank": 29, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 1251, "win_rate": 52.8 }, { "rank": 30, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1239, "win_rate": 52.8 }, { "rank": 31, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1237, "win_rate": 53.1 }, { "rank": 32, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 1235, "win_rate": 51.3 }, { "rank": 33, "permaslug": "x-ai/grok-4.7-20260916", "catalog_id": "x-ai/grok-4.7", "name": "Grok 4.7", "value": 1232, "win_rate": 45 }, { "rank": 34, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 1224, "win_rate": 48.2 }, { "rank": 35, "permaslug": "inception/mercury-3-20261019", "catalog_id": "inception/mercury-3", "name": "Mercury 3", "value": 1206, "win_rate": 45.5 }, { "rank": 36, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek-V4-Flash-0731", "value": 1180, "win_rate": 41.1 }, { "rank": 37, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 1180, "win_rate": 45.1 }, { "rank": 38, "permaslug": "upstage/solar-pro4-20260810", "catalog_id": "upstage/solar-pro4", "name": "Solar Pro 4", "value": 1177, "win_rate": 41.3 }, { "rank": 39, "permaslug": "stepfun/step-3.7-flash-20260528", "catalog_id": "stepfun/step-3.7-flash", "name": "Step 3.7 Flash", "value": 1172, "win_rate": 42.9 }, { "rank": 40, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Inkling", "value": 1156, "win_rate": 37.4 }, { "rank": 41, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra", "value": 1142, "win_rate": 37.5 }, { "rank": 42, "permaslug": "tencent/hy3-20260706", "catalog_id": "tencent/hy3", "name": "Hy3 Low", "value": 1125, "win_rate": 36.1 } ], "id": "da-models-dataviz", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 94 }, { "ranked_count": 42, "scored_count": 42, "truncated": false, "rows": [ { "rank": 1, "permaslug": "inception/mercury-3-20261019", "catalog_id": "inception/mercury-3", "name": "Mercury 3", "value": 57289, "win_rate": 45.5 }, { "rank": 2, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 65148, "win_rate": 45.1 }, { "rank": 3, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 65551, "win_rate": 52.3 }, { "rank": 4, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 70417, "win_rate": 53.1 }, { "rank": 5, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 77521, "win_rate": 52.8 }, { "rank": 6, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 88782, "win_rate": 55.4 }, { "rank": 7, "permaslug": "stepfun/step-3.7-flash-20260528", "catalog_id": "stepfun/step-3.7-flash", "name": "Step 3.7 Flash", "value": 88807, "win_rate": 42.9 }, { "rank": 8, "permaslug": "anthropic/claude-haiku-5.5-20261007", "catalog_id": "anthropic/claude-haiku-5.5", "name": "Claude Haiku 5.5", "value": 91178, "win_rate": 54.3 }, { "rank": 9, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 96954, "win_rate": 51.3 }, { "rank": 10, "permaslug": "tencent/hy3-20260706", "catalog_id": "tencent/hy3", "name": "Hy3 Low", "value": 97319, "win_rate": 36.1 }, { "rank": 11, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Inkling", "value": 97792, "win_rate": 37.4 }, { "rank": 12, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek-V4.1-Flash (1017)", "value": 99794, "win_rate": 51.6 }, { "rank": 13, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 106240, "win_rate": 57.5 }, { "rank": 14, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra", "value": 108078, "win_rate": 37.5 }, { "rank": 15, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 113092, "win_rate": 51.3 }, { "rank": 16, "permaslug": "meta/muse-wonder-20261012", "catalog_id": "meta/muse-wonder", "name": "Muse Wonder (max)", "value": 122132, "win_rate": 55.7 }, { "rank": 17, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 141709, "win_rate": 52.8 }, { "rank": 18, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 146568, "win_rate": 58 }, { "rank": 19, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 155490, "win_rate": 57.7 }, { "rank": 20, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 170107, "win_rate": 49.7 }, { "rank": 21, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 178922, "win_rate": 50.2 }, { "rank": 22, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Gemini 4 Argon", "value": 181312, "win_rate": 61.5 }, { "rank": 23, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Claude Opus 5.5", "value": 181576, "win_rate": 64.8 }, { "rank": 24, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 198095, "win_rate": 52.9 }, { "rank": 25, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 203244, "win_rate": 51.4 }, { "rank": 26, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 Max", "value": 204881, "win_rate": 52.2 }, { "rank": 27, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "value": 206984, "win_rate": 53.7 }, { "rank": 28, "permaslug": "xiaomi/mimo-v2.6-pro-20260921", "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "MiMo-V2.6-Pro", "value": 210597, "win_rate": 58.8 }, { "rank": 29, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 220612, "win_rate": 48.2 }, { "rank": 30, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 225865, "win_rate": 58.5 }, { "rank": 31, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen3.7 Plus", "value": 235208, "win_rate": 51.4 }, { "rank": 32, "permaslug": "upstage/solar-pro4-20260810", "catalog_id": "upstage/solar-pro4", "name": "Solar Pro 4", "value": 235495, "win_rate": 41.3 }, { "rank": 33, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek-V4-Flash-0731", "value": 240959, "win_rate": 41.1 }, { "rank": 34, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Claude Sonnet 5.5", "value": 241869, "win_rate": 67.7 }, { "rank": 35, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 242746, "win_rate": 61.8 }, { "rank": 36, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 246953, "win_rate": 52 }, { "rank": 37, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3", "value": 343727, "win_rate": 52 }, { "rank": 38, "permaslug": "mistralai/mistral-large-4-0-20261006", "catalog_id": "mistralai/mistral-large-4-0", "name": "Mistral Large 4", "value": 356800, "win_rate": 51 }, { "rank": 39, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM-5.3-Flash", "value": 402574, "win_rate": 50.3 }, { "rank": 40, "permaslug": "x-ai/grok-4.7-20260916", "catalog_id": "x-ai/grok-4.7", "name": "Grok 4.7", "value": 554841, "win_rate": 45 }, { "rank": 41, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 657919, "win_rate": 63.2 }, { "rank": 42, "permaslug": "moonshotai/kimi-k3.1-pro-20261023", "catalog_id": "moonshotai/kimi-k3.1-pro", "name": "Kimi K3.1 Pro", "value": 1123642, "win_rate": 56.3 } ], "id": "da-models-dataviz-speed", "source": "design-arena", "group": "speed", "field": "avg_generation_time_ms", "direction": "lower_better", "missing_in_window": 94 }, { "ranked_count": 47, "scored_count": 47, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Claude Opus 5.5", "value": 1438, "win_rate": 66.4 }, { "rank": 2, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Claude Sonnet 5.5", "value": 1414, "win_rate": 62.2 }, { "rank": 3, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "value": 1408, "win_rate": 61 }, { "rank": 4, "permaslug": "moonshotai/kimi-k3.1-pro-20261023", "catalog_id": "moonshotai/kimi-k3.1-pro", "name": "Kimi K3.1 Pro", "value": 1407, "win_rate": 66.5 }, { "rank": 5, "permaslug": "meta/muse-wonder-20261012", "catalog_id": "meta/muse-wonder", "name": "Muse Wonder (max)", "value": 1405, "win_rate": 62.3 }, { "rank": 6, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 1381, "win_rate": 65.6 }, { "rank": 7, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Gemini 4 Argon", "value": 1369, "win_rate": 57.9 }, { "rank": 8, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 1362, "win_rate": 60.2 }, { "rank": 9, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 Max", "value": 1343, "win_rate": 56 }, { "rank": 10, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 1338, "win_rate": 58.3 }, { "rank": 11, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 1335, "win_rate": 60.8 }, { "rank": 12, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 1331, "win_rate": 54.1 }, { "rank": 13, "permaslug": "anthropic/claude-haiku-5.5-20261007", "catalog_id": "anthropic/claude-haiku-5.5", "name": "Claude Haiku 5.5", "value": 1323, "win_rate": 55 }, { "rank": 14, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 1318, "win_rate": 53.5 }, { "rank": 15, "permaslug": "xiaomi/mimo-v2.6-pro-20260921", "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "MiMo-V2.6-Pro", "value": 1315, "win_rate": 53.5 }, { "rank": 16, "permaslug": "x-ai/grok-4.7-20260916", "catalog_id": "x-ai/grok-4.7", "name": "Grok 4.7", "value": 1313, "win_rate": 52.6 }, { "rank": 17, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3", "value": 1307, "win_rate": 52.1 }, { "rank": 18, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 1304, "win_rate": 51 }, { "rank": 19, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 1301, "win_rate": 50.5 }, { "rank": 20, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 1294, "win_rate": 54 }, { "rank": 21, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM-5.3-Flash", "value": 1276, "win_rate": 46.8 }, { "rank": 22, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 1274, "win_rate": 51.1 }, { "rank": 23, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 1269, "win_rate": 48.1 }, { "rank": 24, "permaslug": "meta/muse-spark-open-20261015", "catalog_id": "meta/muse-spark-open", "name": "Muse Spark Open (xhigh)", "value": 1269, "win_rate": 49.8 }, { "rank": 25, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 1266, "win_rate": 49.4 }, { "rank": 26, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek-V4.1-Flash (1017)", "value": 1264, "win_rate": 43.4 }, { "rank": 27, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 1264, "win_rate": 52.6 }, { "rank": 28, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1263, "win_rate": 52.5 }, { "rank": 29, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1262, "win_rate": 52.5 }, { "rank": 30, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 1262, "win_rate": 50.8 }, { "rank": 31, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 1262, "win_rate": 49.2 }, { "rank": 32, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen3.7 Plus", "value": 1260, "win_rate": 49.2 }, { "rank": 33, "permaslug": "mistralai/mistral-large-4-0-20261006", "catalog_id": "mistralai/mistral-large-4-0", "name": "Mistral Large 4", "value": 1226, "win_rate": 42.3 }, { "rank": 34, "permaslug": "inception/mercury-3-20261019", "catalog_id": "inception/mercury-3", "name": "Mercury 3", "value": 1222, "win_rate": 44.2 }, { "rank": 35, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 1220, "win_rate": 47 }, { "rank": 36, "permaslug": "reflection/beam-1.0-501b-a23b-20261016", "catalog_id": "reflection/beam-1.0-501b-a23b", "name": "Beam 1.0 (max)", "value": 1212, "win_rate": 41.4 }, { "rank": 37, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 1211, "win_rate": 45.7 }, { "rank": 38, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek-V4-Flash-0731", "value": 1208, "win_rate": 44.6 }, { "rank": 39, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 1171, "win_rate": 42.8 }, { "rank": 40, "permaslug": "upstage/solar-pro4-20260810", "catalog_id": "upstage/solar-pro4", "name": "Solar Pro 4", "value": 1170, "win_rate": 39.9 }, { "rank": 41, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Inkling", "value": 1164, "win_rate": 37.8 }, { "rank": 42, "permaslug": "stepfun/step-3.7-flash-20260528", "catalog_id": "stepfun/step-3.7-flash", "name": "Step 3.7 Flash", "value": 1156, "win_rate": 37.8 }, { "rank": 43, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra", "value": 1140, "win_rate": 36.1 }, { "rank": 44, "permaslug": "tencent/hy3-20260706", "catalog_id": "tencent/hy3", "name": "Hy3 Low", "value": 1136, "win_rate": 38.6 }, { "rank": 45, "permaslug": "upstage/solar-mini4-20260922", "catalog_id": "upstage/solar-mini4", "name": "Solar Mini 4", "value": 1125, "win_rate": 29.4 }, { "rank": 46, "permaslug": "meta/muse-glimmer-30b-20260810", "catalog_id": "meta/muse-glimmer-30b", "name": "Muse Glimmer 30B (xhigh)", "value": 1122, "win_rate": 31.2 }, { "rank": 47, "permaslug": "nvidia/nemotron-3.5-super-vl-20261015", "catalog_id": "nvidia/nemotron-3.5-super-vl", "name": "Nemotron 3.5 Super VL", "value": 1110, "win_rate": 29.4 } ], "id": "da-models-gamedev", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 89 }, { "ranked_count": 47, "scored_count": 47, "truncated": false, "rows": [ { "rank": 1, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 77412, "win_rate": 42.8 }, { "rank": 2, "permaslug": "inception/mercury-3-20261019", "catalog_id": "inception/mercury-3", "name": "Mercury 3", "value": 77489, "win_rate": 44.2 }, { "rank": 3, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 81345, "win_rate": 50.8 }, { "rank": 4, "permaslug": "meta/muse-glimmer-30b-20260810", "catalog_id": "meta/muse-glimmer-30b", "name": "Muse Glimmer 30B (xhigh)", "value": 88863, "win_rate": 31.2 }, { "rank": 5, "permaslug": "tencent/hy3-20260706", "catalog_id": "tencent/hy3", "name": "Hy3 Low", "value": 89395, "win_rate": 38.6 }, { "rank": 6, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 98095, "win_rate": 52.5 }, { "rank": 7, "permaslug": "nvidia/nemotron-3.5-super-vl-20261015", "catalog_id": "nvidia/nemotron-3.5-super-vl", "name": "Nemotron 3.5 Super VL", "value": 105876, "win_rate": 29.4 }, { "rank": 8, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 107940, "win_rate": 51 }, { "rank": 9, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 110292, "win_rate": 53.5 }, { "rank": 10, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek-V4.1-Flash (1017)", "value": 113547, "win_rate": 43.4 }, { "rank": 11, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 118084, "win_rate": 45.7 }, { "rank": 12, "permaslug": "reflection/beam-1.0-501b-a23b-20261016", "catalog_id": "reflection/beam-1.0-501b-a23b", "name": "Beam 1.0 (max)", "value": 120501, "win_rate": 41.4 }, { "rank": 13, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra", "value": 131313, "win_rate": 36.1 }, { "rank": 14, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Inkling", "value": 144247, "win_rate": 37.8 }, { "rank": 15, "permaslug": "stepfun/step-3.7-flash-20260528", "catalog_id": "stepfun/step-3.7-flash", "name": "Step 3.7 Flash", "value": 149922, "win_rate": 37.8 }, { "rank": 16, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 153368, "win_rate": 52.5 }, { "rank": 17, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 197916, "win_rate": 54.1 }, { "rank": 18, "permaslug": "meta/muse-spark-open-20261015", "catalog_id": "meta/muse-spark-open", "name": "Muse Spark Open (xhigh)", "value": 199936, "win_rate": 49.8 }, { "rank": 19, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 206534, "win_rate": 48.1 }, { "rank": 20, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 206916, "win_rate": 50.5 }, { "rank": 21, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Gemini 4 Argon", "value": 212476, "win_rate": 57.9 }, { "rank": 22, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 216485, "win_rate": 49.2 }, { "rank": 23, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 218767, "win_rate": 60.8 }, { "rank": 24, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 221038, "win_rate": 52.6 }, { "rank": 25, "permaslug": "meta/muse-wonder-20261012", "catalog_id": "meta/muse-wonder", "name": "Muse Wonder (max)", "value": 236181, "win_rate": 62.3 }, { "rank": 26, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen3.7 Plus", "value": 254339, "win_rate": 49.2 }, { "rank": 27, "permaslug": "anthropic/claude-haiku-5.5-20261007", "catalog_id": "anthropic/claude-haiku-5.5", "name": "Claude Haiku 5.5", "value": 258253, "win_rate": 55 }, { "rank": 28, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "value": 260480, "win_rate": 61 }, { "rank": 29, "permaslug": "upstage/solar-mini4-20260922", "catalog_id": "upstage/solar-mini4", "name": "Solar Mini 4", "value": 270808, "win_rate": 29.4 }, { "rank": 30, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 Max", "value": 279537, "win_rate": 56 }, { "rank": 31, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek-V4-Flash-0731", "value": 293083, "win_rate": 44.6 }, { "rank": 32, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 300013, "win_rate": 47 }, { "rank": 33, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 329748, "win_rate": 54 }, { "rank": 34, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 333963, "win_rate": 49.4 }, { "rank": 35, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 338409, "win_rate": 51.1 }, { "rank": 36, "permaslug": "xiaomi/mimo-v2.6-pro-20260921", "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "MiMo-V2.6-Pro", "value": 344915, "win_rate": 53.5 }, { "rank": 37, "permaslug": "mistralai/mistral-large-4-0-20261006", "catalog_id": "mistralai/mistral-large-4-0", "name": "Mistral Large 4", "value": 353788, "win_rate": 42.3 }, { "rank": 38, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 380919, "win_rate": 65.6 }, { "rank": 39, "permaslug": "upstage/solar-pro4-20260810", "catalog_id": "upstage/solar-pro4", "name": "Solar Pro 4", "value": 382003, "win_rate": 39.9 }, { "rank": 40, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 394799, "win_rate": 58.3 }, { "rank": 41, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Claude Opus 5.5", "value": 464750, "win_rate": 66.4 }, { "rank": 42, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3", "value": 476564, "win_rate": 52.1 }, { "rank": 43, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Claude Sonnet 5.5", "value": 481343, "win_rate": 62.2 }, { "rank": 44, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM-5.3-Flash", "value": 623842, "win_rate": 46.8 }, { "rank": 45, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 980127, "win_rate": 60.2 }, { "rank": 46, "permaslug": "x-ai/grok-4.7-20260916", "catalog_id": "x-ai/grok-4.7", "name": "Grok 4.7", "value": 1066972, "win_rate": 52.6 }, { "rank": 47, "permaslug": "moonshotai/kimi-k3.1-pro-20261023", "catalog_id": "moonshotai/kimi-k3.1-pro", "name": "Kimi K3.1 Pro", "value": 1154372, "win_rate": 66.5 } ], "id": "da-models-gamedev-speed", "source": "design-arena", "group": "speed", "field": "avg_generation_time_ms", "direction": "lower_better", "missing_in_window": 89 }, { "ranked_count": 33, "scored_count": 33, "truncated": false, "rows": [ { "rank": 1, "permaslug": "moonshotai/kimi-k3.1-pro-20261023", "catalog_id": "moonshotai/kimi-k3.1-pro", "name": "Kimi K3.1 Pro", "value": 1327, "win_rate": 62.4 }, { "rank": 2, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Claude Opus 5.5", "value": 1322, "win_rate": 52.2 }, { "rank": 3, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Gemini 4 Argon", "value": 1322, "win_rate": 60.3 }, { "rank": 4, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 Max", "value": 1317, "win_rate": 54.5 }, { "rank": 5, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 1306, "win_rate": 58.2 }, { "rank": 6, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 1300, "win_rate": 59.6 }, { "rank": 7, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 1299, "win_rate": 55.8 }, { "rank": 8, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 1298, "win_rate": 62.6 }, { "rank": 9, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 1296, "win_rate": 56.4 }, { "rank": 10, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 1291, "win_rate": 54.9 }, { "rank": 11, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3", "value": 1287, "win_rate": 56.6 }, { "rank": 12, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM-5.3-Flash", "value": 1280, "win_rate": 56.4 }, { "rank": 13, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 1279, "win_rate": 54 }, { "rank": 14, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 1279, "win_rate": 55 }, { "rank": 15, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1251, "win_rate": 58.3 }, { "rank": 16, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek-V4.1-Flash (1017)", "value": 1241, "win_rate": 51.5 }, { "rank": 17, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 1236, "win_rate": 48.9 }, { "rank": 18, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 1229, "win_rate": 48.9 }, { "rank": 19, "permaslug": "mistralai/mistral-large-4-0-20261006", "catalog_id": "mistralai/mistral-large-4-0", "name": "Mistral Large 4", "value": 1229, "win_rate": 45.3 }, { "rank": 20, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 1213, "win_rate": 55.2 }, { "rank": 21, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 1209, "win_rate": 47.8 }, { "rank": 22, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 1208, "win_rate": 48.3 }, { "rank": 23, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen3.7 Plus", "value": 1202, "win_rate": 46.5 }, { "rank": 24, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1192, "win_rate": 51.4 }, { "rank": 25, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 1188, "win_rate": 49.2 }, { "rank": 26, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek-V4-Flash-0731", "value": 1180, "win_rate": 45.1 }, { "rank": 27, "permaslug": "inception/mercury-3-20261019", "catalog_id": "inception/mercury-3", "name": "Mercury 3", "value": 1175, "win_rate": 43.1 }, { "rank": 28, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 1172, "win_rate": 44.2 }, { "rank": 29, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 1157, "win_rate": 44.9 }, { "rank": 30, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Inkling", "value": 1105, "win_rate": 34.3 }, { "rank": 31, "permaslug": "stepfun/step-3.7-flash-20260528", "catalog_id": "stepfun/step-3.7-flash", "name": "Step 3.7 Flash", "value": 1079, "win_rate": 36.8 }, { "rank": 32, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 1078, "win_rate": 37 }, { "rank": 33, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra", "value": 1066, "win_rate": 32.3 } ], "id": "da-models-svg", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 103 }, { "ranked_count": 33, "scored_count": 33, "truncated": false, "rows": [ { "rank": 1, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 27047, "win_rate": 37 }, { "rank": 2, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 33675, "win_rate": 51.4 }, { "rank": 3, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Inkling", "value": 36953, "win_rate": 34.3 }, { "rank": 4, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra", "value": 39351, "win_rate": 32.3 }, { "rank": 5, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Claude Opus 5.5", "value": 43670, "win_rate": 52.2 }, { "rank": 6, "permaslug": "inception/mercury-3-20261019", "catalog_id": "inception/mercury-3", "name": "Mercury 3", "value": 50937, "win_rate": 43.1 }, { "rank": 7, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 53614, "win_rate": 44.9 }, { "rank": 8, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 54518, "win_rate": 54 }, { "rank": 9, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 56620, "win_rate": 54.9 }, { "rank": 10, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 59539, "win_rate": 62.6 }, { "rank": 11, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 60318, "win_rate": 49.2 }, { "rank": 12, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 63543, "win_rate": 47.8 }, { "rank": 13, "permaslug": "stepfun/step-3.7-flash-20260528", "catalog_id": "stepfun/step-3.7-flash", "name": "Step 3.7 Flash", "value": 64267, "win_rate": 36.8 }, { "rank": 14, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 77194, "win_rate": 55.8 }, { "rank": 15, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 79029, "win_rate": 56.4 }, { "rank": 16, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 80250, "win_rate": 58.3 }, { "rank": 17, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek-V4.1-Flash (1017)", "value": 89662, "win_rate": 51.5 }, { "rank": 18, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Gemini 4 Argon", "value": 92731, "win_rate": 60.3 }, { "rank": 19, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 96719, "win_rate": 55.2 }, { "rank": 20, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 106711, "win_rate": 58.2 }, { "rank": 21, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen3.7 Plus", "value": 110987, "win_rate": 46.5 }, { "rank": 22, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 116399, "win_rate": 48.9 }, { "rank": 23, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 142028, "win_rate": 44.2 }, { "rank": 24, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 150083, "win_rate": 55 }, { "rank": 25, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 Max", "value": 156380, "win_rate": 54.5 }, { "rank": 26, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 168336, "win_rate": 48.3 }, { "rank": 27, "permaslug": "mistralai/mistral-large-4-0-20261006", "catalog_id": "mistralai/mistral-large-4-0", "name": "Mistral Large 4", "value": 178837, "win_rate": 45.3 }, { "rank": 28, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM-5.3-Flash", "value": 211812, "win_rate": 56.4 }, { "rank": 29, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek-V4-Flash-0731", "value": 219674, "win_rate": 45.1 }, { "rank": 30, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 234732, "win_rate": 48.9 }, { "rank": 31, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3", "value": 270411, "win_rate": 56.6 }, { "rank": 32, "permaslug": "moonshotai/kimi-k3.1-pro-20261023", "catalog_id": "moonshotai/kimi-k3.1-pro", "name": "Kimi K3.1 Pro", "value": 347173, "win_rate": 62.4 }, { "rank": 33, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 444841, "win_rate": 59.6 } ], "id": "da-models-svg-speed", "source": "design-arena", "group": "speed", "field": "avg_generation_time_ms", "direction": "lower_better", "missing_in_window": 103 }, { "ranked_count": 45, "scored_count": 45, "truncated": false, "rows": [ { "rank": 1, "permaslug": "moonshotai/kimi-k3.1-pro-20261023", "catalog_id": "moonshotai/kimi-k3.1-pro", "name": "Kimi K3.1 Pro", "value": 1397, "win_rate": 66.2 }, { "rank": 2, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Claude Opus 5.5", "value": 1377, "win_rate": 63.5 }, { "rank": 3, "permaslug": "meta/muse-wonder-20261012", "catalog_id": "meta/muse-wonder", "name": "Muse Wonder (max)", "value": 1377, "win_rate": 63.2 }, { "rank": 4, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Claude Sonnet 5.5", "value": 1375, "win_rate": 63.3 }, { "rank": 5, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 1345, "win_rate": 60.8 }, { "rank": 6, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 1345, "win_rate": 57.8 }, { "rank": 7, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 Max", "value": 1342, "win_rate": 57.6 }, { "rank": 8, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "value": 1339, "win_rate": 58 }, { "rank": 9, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 1338, "win_rate": 59.9 }, { "rank": 10, "permaslug": "meta/muse-spark-open-20261015", "catalog_id": "meta/muse-spark-open", "name": "Muse Spark Open (xhigh)", "value": 1338, "win_rate": 59 }, { "rank": 11, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 1333, "win_rate": 59.6 }, { "rank": 12, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Gemini 4 Argon", "value": 1333, "win_rate": 57.8 }, { "rank": 13, "permaslug": "xiaomi/mimo-v2.6-pro-20260921", "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "MiMo-V2.6-Pro", "value": 1333, "win_rate": 59 }, { "rank": 14, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 1314, "win_rate": 53.9 }, { "rank": 15, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 1313, "win_rate": 58.1 }, { "rank": 16, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM-5.3-Flash", "value": 1309, "win_rate": 54.1 }, { "rank": 17, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3", "value": 1306, "win_rate": 56.2 }, { "rank": 18, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek-V4.1-Flash (1017)", "value": 1300, "win_rate": 53.3 }, { "rank": 19, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 1296, "win_rate": 51.9 }, { "rank": 20, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 1293, "win_rate": 53.8 }, { "rank": 21, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 1293, "win_rate": 51.9 }, { "rank": 22, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 1291, "win_rate": 55.3 }, { "rank": 23, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 1290, "win_rate": 53.1 }, { "rank": 24, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 1283, "win_rate": 51 }, { "rank": 25, "permaslug": "anthropic/claude-haiku-5.5-20261007", "catalog_id": "anthropic/claude-haiku-5.5", "name": "Claude Haiku 5.5", "value": 1277, "win_rate": 50.7 }, { "rank": 26, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 1275, "win_rate": 51.5 }, { "rank": 27, "permaslug": "x-ai/grok-4.7-20260916", "catalog_id": "x-ai/grok-4.7", "name": "Grok 4.7", "value": 1274, "win_rate": 48.9 }, { "rank": 28, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 1273, "win_rate": 53.6 }, { "rank": 29, "permaslug": "mistralai/mistral-large-4-0-20261006", "catalog_id": "mistralai/mistral-large-4-0", "name": "Mistral Large 4", "value": 1269, "win_rate": 47.6 }, { "rank": 30, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1267, "win_rate": 54.1 }, { "rank": 31, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 1265, "win_rate": 53.2 }, { "rank": 32, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen3.7 Plus", "value": 1257, "win_rate": 48.8 }, { "rank": 33, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 1254, "win_rate": 50.5 }, { "rank": 34, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1253, "win_rate": 53 }, { "rank": 35, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 1241, "win_rate": 50.6 }, { "rank": 36, "permaslug": "inception/mercury-3-20261019", "catalog_id": "inception/mercury-3", "name": "Mercury 3", "value": 1233, "win_rate": 45.4 }, { "rank": 37, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek-V4-Flash-0731", "value": 1230, "win_rate": 46.8 }, { "rank": 38, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Inkling", "value": 1196, "win_rate": 40.5 }, { "rank": 39, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 1189, "win_rate": 45 }, { "rank": 40, "permaslug": "stepfun/step-3.7-flash-20260528", "catalog_id": "stepfun/step-3.7-flash", "name": "Step 3.7 Flash", "value": 1175, "win_rate": 42 }, { "rank": 41, "permaslug": "tencent/hy3-20260706", "catalog_id": "tencent/hy3", "name": "Hy3 Low", "value": 1158, "win_rate": 40.2 }, { "rank": 42, "permaslug": "upstage/solar-pro4-20260810", "catalog_id": "upstage/solar-pro4", "name": "Solar Pro 4", "value": 1145, "win_rate": 35.5 }, { "rank": 43, "permaslug": "nvidia/nemotron-3.5-super-vl-20261015", "catalog_id": "nvidia/nemotron-3.5-super-vl", "name": "Nemotron 3.5 Super VL", "value": 1143, "win_rate": 30.8 }, { "rank": 44, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra", "value": 1136, "win_rate": 35.9 }, { "rank": 45, "permaslug": "upstage/solar-mini4-20260922", "catalog_id": "upstage/solar-mini4", "name": "Solar Mini 4", "value": 1088, "win_rate": 26.5 } ], "id": "da-models-uicomponent", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 91 }, { "ranked_count": 45, "scored_count": 45, "truncated": false, "rows": [ { "rank": 1, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 52158, "win_rate": 45 }, { "rank": 2, "permaslug": "inception/mercury-3-20261019", "catalog_id": "inception/mercury-3", "name": "Mercury 3", "value": 53120, "win_rate": 45.4 }, { "rank": 3, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 66180, "win_rate": 53.8 }, { "rank": 4, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 68425, "win_rate": 54.1 }, { "rank": 5, "permaslug": "nvidia/nemotron-3.5-super-vl-20261015", "catalog_id": "nvidia/nemotron-3.5-super-vl", "name": "Nemotron 3.5 Super VL", "value": 71038, "win_rate": 30.8 }, { "rank": 6, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 87517, "win_rate": 53 }, { "rank": 7, "permaslug": "anthropic/claude-haiku-5.5-20261007", "catalog_id": "anthropic/claude-haiku-5.5", "name": "Claude Haiku 5.5", "value": 87526, "win_rate": 50.7 }, { "rank": 8, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 89069, "win_rate": 53.9 }, { "rank": 9, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 89292, "win_rate": 51.9 }, { "rank": 10, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra", "value": 101858, "win_rate": 35.9 }, { "rank": 11, "permaslug": "stepfun/step-3.7-flash-20260528", "catalog_id": "stepfun/step-3.7-flash", "name": "Step 3.7 Flash", "value": 102699, "win_rate": 42 }, { "rank": 12, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 117355, "win_rate": 57.8 }, { "rank": 13, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 129431, "win_rate": 50.6 }, { "rank": 14, "permaslug": "tencent/hy3-20260706", "catalog_id": "tencent/hy3", "name": "Hy3 Low", "value": 129643, "win_rate": 40.2 }, { "rank": 15, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 132191, "win_rate": 58.1 }, { "rank": 16, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 136886, "win_rate": 53.6 }, { "rank": 17, "permaslug": "meta/muse-wonder-20261012", "catalog_id": "meta/muse-wonder", "name": "Muse Wonder (max)", "value": 140349, "win_rate": 63.2 }, { "rank": 18, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 140875, "win_rate": 51.5 }, { "rank": 19, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Gemini 4 Argon", "value": 145700, "win_rate": 57.8 }, { "rank": 20, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Inkling", "value": 152108, "win_rate": 40.5 }, { "rank": 21, "permaslug": "meta/muse-spark-open-20261015", "catalog_id": "meta/muse-spark-open", "name": "Muse Spark Open (xhigh)", "value": 162285, "win_rate": 59 }, { "rank": 22, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 167884, "win_rate": 51.9 }, { "rank": 23, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 169851, "win_rate": 51 }, { "rank": 24, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "value": 183884, "win_rate": 58 }, { "rank": 25, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek-V4.1-Flash (1017)", "value": 188427, "win_rate": 53.3 }, { "rank": 26, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 Max", "value": 191697, "win_rate": 57.6 }, { "rank": 27, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 206997, "win_rate": 53.2 }, { "rank": 28, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Claude Opus 5.5", "value": 207459, "win_rate": 63.5 }, { "rank": 29, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 215969, "win_rate": 59.6 }, { "rank": 30, "permaslug": "xiaomi/mimo-v2.6-pro-20260921", "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "MiMo-V2.6-Pro", "value": 220051, "win_rate": 59 }, { "rank": 31, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 222825, "win_rate": 60.8 }, { "rank": 32, "permaslug": "upstage/solar-mini4-20260922", "catalog_id": "upstage/solar-mini4", "name": "Solar Mini 4", "value": 224565, "win_rate": 26.5 }, { "rank": 33, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen3.7 Plus", "value": 224747, "win_rate": 48.8 }, { "rank": 34, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Claude Sonnet 5.5", "value": 226232, "win_rate": 63.3 }, { "rank": 35, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek-V4-Flash-0731", "value": 229039, "win_rate": 46.8 }, { "rank": 36, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 231305, "win_rate": 50.5 }, { "rank": 37, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 252790, "win_rate": 53.1 }, { "rank": 38, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 260417, "win_rate": 55.3 }, { "rank": 39, "permaslug": "upstage/solar-pro4-20260810", "catalog_id": "upstage/solar-pro4", "name": "Solar Pro 4", "value": 266332, "win_rate": 35.5 }, { "rank": 40, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM-5.3-Flash", "value": 325022, "win_rate": 54.1 }, { "rank": 41, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3", "value": 333030, "win_rate": 56.2 }, { "rank": 42, "permaslug": "mistralai/mistral-large-4-0-20261006", "catalog_id": "mistralai/mistral-large-4-0", "name": "Mistral Large 4", "value": 396754, "win_rate": 47.6 }, { "rank": 43, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 764798, "win_rate": 59.9 }, { "rank": 44, "permaslug": "x-ai/grok-4.7-20260916", "catalog_id": "x-ai/grok-4.7", "name": "Grok 4.7", "value": 768347, "win_rate": 48.9 }, { "rank": 45, "permaslug": "moonshotai/kimi-k3.1-pro-20261023", "catalog_id": "moonshotai/kimi-k3.1-pro", "name": "Kimi K3.1 Pro", "value": 996844, "win_rate": 66.2 } ], "id": "da-models-uicomponent-speed", "source": "design-arena", "group": "speed", "field": "avg_generation_time_ms", "direction": "lower_better", "missing_in_window": 91 }, { "ranked_count": 47, "scored_count": 47, "truncated": false, "rows": [ { "rank": 1, "permaslug": "meta/muse-wonder-20261012", "catalog_id": "meta/muse-wonder", "name": "Muse Wonder (max)", "value": 1366, "win_rate": 62.7 }, { "rank": 2, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 1355, "win_rate": 58.1 }, { "rank": 3, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 Max", "value": 1344, "win_rate": 56.3 }, { "rank": 4, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 1335, "win_rate": 59.4 }, { "rank": 5, "permaslug": "moonshotai/kimi-k3.1-pro-20261023", "catalog_id": "moonshotai/kimi-k3.1-pro", "name": "Kimi K3.1 Pro", "value": 1326, "win_rate": 58 }, { "rank": 6, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Claude Opus 5.5", "value": 1325, "win_rate": 55.5 }, { "rank": 7, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Claude Sonnet 5.5", "value": 1321, "win_rate": 54.4 }, { "rank": 8, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Gemini 4 Argon", "value": 1316, "win_rate": 56.3 }, { "rank": 9, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "value": 1315, "win_rate": 54.2 }, { "rank": 10, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 1312, "win_rate": 56.3 }, { "rank": 11, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 1311, "win_rate": 52.2 }, { "rank": 12, "permaslug": "meta/muse-spark-open-20261015", "catalog_id": "meta/muse-spark-open", "name": "Muse Spark Open (xhigh)", "value": 1310, "win_rate": 55.5 }, { "rank": 13, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 1309, "win_rate": 56 }, { "rank": 14, "permaslug": "xiaomi/mimo-v2.6-pro-20260921", "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "MiMo-V2.6-Pro", "value": 1306, "win_rate": 50.7 }, { "rank": 15, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 1302, "win_rate": 54 }, { "rank": 16, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 1299, "win_rate": 55.4 }, { "rank": 17, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 1299, "win_rate": 50.1 }, { "rank": 18, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek-V4.1-Flash (1017)", "value": 1298, "win_rate": 52.7 }, { "rank": 19, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 1294, "win_rate": 56 }, { "rank": 20, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3", "value": 1292, "win_rate": 53.8 }, { "rank": 21, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 1287, "win_rate": 52.2 }, { "rank": 22, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 1283, "win_rate": 49.5 }, { "rank": 23, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 1279, "win_rate": 52.3 }, { "rank": 24, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 1273, "win_rate": 52.3 }, { "rank": 25, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 1273, "win_rate": 54.5 }, { "rank": 26, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM-5.3-Flash", "value": 1270, "win_rate": 48.4 }, { "rank": 27, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 1269, "win_rate": 51.3 }, { "rank": 28, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen3.7 Plus", "value": 1267, "win_rate": 50.4 }, { "rank": 29, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1266, "win_rate": 53.7 }, { "rank": 30, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 1262, "win_rate": 51.1 }, { "rank": 31, "permaslug": "anthropic/claude-haiku-5.5-20261007", "catalog_id": "anthropic/claude-haiku-5.5", "name": "Claude Haiku 5.5", "value": 1261, "win_rate": 48.5 }, { "rank": 32, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1257, "win_rate": 52.8 }, { "rank": 33, "permaslug": "mistralai/mistral-large-4-0-20261006", "catalog_id": "mistralai/mistral-large-4-0", "name": "Mistral Large 4", "value": 1256, "win_rate": 47.3 }, { "rank": 34, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 1255, "win_rate": 51.6 }, { "rank": 35, "permaslug": "x-ai/grok-4.7-20260916", "catalog_id": "x-ai/grok-4.7", "name": "Grok 4.7", "value": 1253, "win_rate": 46.1 }, { "rank": 36, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek-V4-Flash-0731", "value": 1236, "win_rate": 46.7 }, { "rank": 37, "permaslug": "inception/mercury-3-20261019", "catalog_id": "inception/mercury-3", "name": "Mercury 3", "value": 1227, "win_rate": 45.3 }, { "rank": 38, "permaslug": "reflection/beam-1.0-501b-a23b-20261016", "catalog_id": "reflection/beam-1.0-501b-a23b", "name": "Beam 1.0 (max)", "value": 1226, "win_rate": 43.3 }, { "rank": 39, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Inkling", "value": 1223, "win_rate": 44.6 }, { "rank": 40, "permaslug": "stepfun/step-3.7-flash-20260528", "catalog_id": "stepfun/step-3.7-flash", "name": "Step 3.7 Flash", "value": 1195, "win_rate": 43.9 }, { "rank": 41, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 1194, "win_rate": 44.1 }, { "rank": 42, "permaslug": "tencent/hy3-20260706", "catalog_id": "tencent/hy3", "name": "Hy3 Low", "value": 1180, "win_rate": 41.3 }, { "rank": 43, "permaslug": "upstage/solar-pro4-20260810", "catalog_id": "upstage/solar-pro4", "name": "Solar Pro 4", "value": 1176, "win_rate": 37.5 }, { "rank": 44, "permaslug": "nvidia/nemotron-3.5-super-vl-20261015", "catalog_id": "nvidia/nemotron-3.5-super-vl", "name": "Nemotron 3.5 Super VL", "value": 1168, "win_rate": 34.8 }, { "rank": 45, "permaslug": "upstage/solar-mini4-20260922", "catalog_id": "upstage/solar-mini4", "name": "Solar Mini 4", "value": 1154, "win_rate": 33 }, { "rank": 46, "permaslug": "meta/muse-glimmer-30b-20260810", "catalog_id": "meta/muse-glimmer-30b", "name": "Muse Glimmer 30B (xhigh)", "value": 1153, "win_rate": 33.7 }, { "rank": 47, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra", "value": 1144, "win_rate": 35.2 } ], "id": "da-models-website", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 89 }, { "ranked_count": 47, "scored_count": 47, "truncated": false, "rows": [ { "rank": 1, "permaslug": "inception/mercury-3-20261019", "catalog_id": "inception/mercury-3", "name": "Mercury 3", "value": 54664, "win_rate": 45.3 }, { "rank": 2, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 68706, "win_rate": 44.1 }, { "rank": 3, "permaslug": "meta/muse-glimmer-30b-20260810", "catalog_id": "meta/muse-glimmer-30b", "name": "Muse Glimmer 30B (xhigh)", "value": 84184, "win_rate": 33.7 }, { "rank": 4, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 88694, "win_rate": 55.4 }, { "rank": 5, "permaslug": "reflection/beam-1.0-501b-a23b-20261016", "catalog_id": "reflection/beam-1.0-501b-a23b", "name": "Beam 1.0 (max)", "value": 89156, "win_rate": 43.3 }, { "rank": 6, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 90270, "win_rate": 53.7 }, { "rank": 7, "permaslug": "nvidia/nemotron-3.5-super-vl-20261015", "catalog_id": "nvidia/nemotron-3.5-super-vl", "name": "Nemotron 3.5 Super VL", "value": 110635, "win_rate": 34.8 }, { "rank": 8, "permaslug": "stepfun/step-3.7-flash-20260528", "catalog_id": "stepfun/step-3.7-flash", "name": "Step 3.7 Flash", "value": 119681, "win_rate": 43.9 }, { "rank": 9, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 123396, "win_rate": 52.8 }, { "rank": 10, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Inkling", "value": 136847, "win_rate": 44.6 }, { "rank": 11, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 136876, "win_rate": 50.1 }, { "rank": 12, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 138321, "win_rate": 54 }, { "rank": 13, "permaslug": "tencent/hy3-20260706", "catalog_id": "tencent/hy3", "name": "Hy3 Low", "value": 146435, "win_rate": 41.3 }, { "rank": 14, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra", "value": 150751, "win_rate": 35.2 }, { "rank": 15, "permaslug": "meta/muse-wonder-20261012", "catalog_id": "meta/muse-wonder", "name": "Muse Wonder (max)", "value": 154249, "win_rate": 62.7 }, { "rank": 16, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 161727, "win_rate": 52.2 }, { "rank": 17, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 169077, "win_rate": 51.6 }, { "rank": 18, "permaslug": "anthropic/claude-haiku-5.5-20261007", "catalog_id": "anthropic/claude-haiku-5.5", "name": "Claude Haiku 5.5", "value": 170825, "win_rate": 48.5 }, { "rank": 19, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 171272, "win_rate": 56 }, { "rank": 20, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 187804, "win_rate": 52.3 }, { "rank": 21, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 196134, "win_rate": 51.3 }, { "rank": 22, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 196150, "win_rate": 58.1 }, { "rank": 23, "permaslug": "meta/muse-spark-open-20261015", "catalog_id": "meta/muse-spark-open", "name": "Muse Spark Open (xhigh)", "value": 205661, "win_rate": 55.5 }, { "rank": 24, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 208403, "win_rate": 49.5 }, { "rank": 25, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 223156, "win_rate": 52.3 }, { "rank": 26, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek-V4-Flash-0731", "value": 239297, "win_rate": 46.7 }, { "rank": 27, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Gemini 4 Argon", "value": 244635, "win_rate": 56.3 }, { "rank": 28, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 Max", "value": 252605, "win_rate": 56.3 }, { "rank": 29, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek-V4.1-Flash (1017)", "value": 257057, "win_rate": 52.7 }, { "rank": 30, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 275586, "win_rate": 54.5 }, { "rank": 31, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Claude Sonnet 5.5", "value": 282195, "win_rate": 54.4 }, { "rank": 32, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "value": 287182, "win_rate": 54.2 }, { "rank": 33, "permaslug": "upstage/solar-pro4-20260810", "catalog_id": "upstage/solar-pro4", "name": "Solar Pro 4", "value": 290312, "win_rate": 37.5 }, { "rank": 34, "permaslug": "upstage/solar-mini4-20260922", "catalog_id": "upstage/solar-mini4", "name": "Solar Mini 4", "value": 290898, "win_rate": 33 }, { "rank": 35, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Claude Opus 5.5", "value": 310104, "win_rate": 55.5 }, { "rank": 36, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 316343, "win_rate": 56 }, { "rank": 37, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 319108, "win_rate": 52.2 }, { "rank": 38, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 323669, "win_rate": 56.3 }, { "rank": 39, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen3.7 Plus", "value": 324794, "win_rate": 50.4 }, { "rank": 40, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 326401, "win_rate": 51.1 }, { "rank": 41, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM-5.3-Flash", "value": 346556, "win_rate": 48.4 }, { "rank": 42, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3", "value": 352899, "win_rate": 53.8 }, { "rank": 43, "permaslug": "mistralai/mistral-large-4-0-20261006", "catalog_id": "mistralai/mistral-large-4-0", "name": "Mistral Large 4", "value": 415136, "win_rate": 47.3 }, { "rank": 44, "permaslug": "xiaomi/mimo-v2.6-pro-20260921", "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "MiMo-V2.6-Pro", "value": 491690, "win_rate": 50.7 }, { "rank": 45, "permaslug": "x-ai/grok-4.7-20260916", "catalog_id": "x-ai/grok-4.7", "name": "Grok 4.7", "value": 736995, "win_rate": 46.1 }, { "rank": 46, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 860248, "win_rate": 59.4 }, { "rank": 47, "permaslug": "moonshotai/kimi-k3.1-pro-20261023", "catalog_id": "moonshotai/kimi-k3.1-pro", "name": "Kimi K3.1 Pro", "value": 1225698, "win_rate": 58 } ], "id": "da-models-website-speed", "source": "design-arena", "group": "speed", "field": "avg_generation_time_ms", "direction": "lower_better", "missing_in_window": 89 }, { "ranked_count": 17, "scored_count": 17, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 1249, "win_rate": 61.9 }, { "rank": 2, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 1225, "win_rate": 53.4 }, { "rank": 3, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 1218, "win_rate": 55 }, { "rank": 4, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1203, "win_rate": 55.5 }, { "rank": 5, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 1202, "win_rate": 55.9 }, { "rank": 6, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 1200, "win_rate": 52 }, { "rank": 7, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 1190, "win_rate": 51.8 }, { "rank": 8, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 1174, "win_rate": 46.7 }, { "rank": 9, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 1171, "win_rate": 49.1 }, { "rank": 10, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 1147, "win_rate": 48.1 }, { "rank": 11, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1146, "win_rate": 55.4 }, { "rank": 12, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 1144, "win_rate": 47.5 }, { "rank": 13, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 1142, "win_rate": 42.4 }, { "rank": 14, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 1125, "win_rate": 44.1 }, { "rank": 15, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 1125, "win_rate": 46.1 }, { "rank": 16, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 1095, "win_rate": 43 }, { "rank": 17, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 972, "win_rate": 28.7 } ], "id": "da-agents-agenticgamedev", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 118 }, { "ranked_count": 4, "scored_count": 4, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 1254, "win_rate": 59.4 }, { "rank": 2, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1227, "win_rate": 55.6 }, { "rank": 3, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1162, "win_rate": 45.8 }, { "rank": 4, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 1066, "win_rate": 31.8 } ], "id": "da-agents-agentichtmlslides", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 131 }, { "ranked_count": 3, "scored_count": 3, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1294, "win_rate": 64.8 }, { "rank": 2, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1244, "win_rate": 57.5 }, { "rank": 3, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 1072, "win_rate": 31.9 } ], "id": "da-agents-agenticslides", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 132 }, { "ranked_count": 4, "scored_count": 4, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 1252, "win_rate": 59.5 }, { "rank": 2, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1230, "win_rate": 56 }, { "rank": 3, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1162, "win_rate": 45.7 }, { "rank": 4, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 1066, "win_rate": 31.7 } ], "id": "da-agents-agenticslides(html)", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 131 }, { "ranked_count": 3, "scored_count": 3, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1310, "win_rate": 68.9 }, { "rank": 2, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1242, "win_rate": 57.8 }, { "rank": 3, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 1068, "win_rate": 32.4 } ], "id": "da-agents-agenticslides(python-pptx)", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 132 }, { "ranked_count": 18, "scored_count": 18, "truncated": false, "rows": [ { "rank": 1, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 1294, "win_rate": 61.5 }, { "rank": 2, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 1285, "win_rate": 65.1 }, { "rank": 3, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 1256, "win_rate": 56.2 }, { "rank": 4, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 1254, "win_rate": 55.3 }, { "rank": 5, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 1244, "win_rate": 53.3 }, { "rank": 6, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1236, "win_rate": 56.4 }, { "rank": 7, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 1236, "win_rate": 63.6 }, { "rank": 8, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 1229, "win_rate": 54.5 }, { "rank": 9, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 1225, "win_rate": 53.3 }, { "rank": 10, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 1205, "win_rate": 53.4 }, { "rank": 11, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1186, "win_rate": 57.6 }, { "rank": 12, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 1180, "win_rate": 52.9 }, { "rank": 13, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 1173, "win_rate": 46.7 }, { "rank": 14, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 1162, "win_rate": 44.6 }, { "rank": 15, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 1161, "win_rate": 48.4 }, { "rank": 16, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 1139, "win_rate": 46 }, { "rank": 17, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 1082, "win_rate": 33.4 }, { "rank": 18, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 966, "win_rate": 22.8 } ], "id": "da-agents-androidnative", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 117 }, { "ranked_count": 21, "scored_count": 21, "truncated": false, "rows": [ { "rank": 1, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Gemini 4 Argon", "value": 1438, "win_rate": 77.5 }, { "rank": 2, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "value": 1362, "win_rate": 71.7 }, { "rank": 3, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Claude Sonnet 5.5", "value": 1303, "win_rate": 64 }, { "rank": 4, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Claude Opus 5.5", "value": 1273, "win_rate": 58.7 }, { "rank": 5, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 1232, "win_rate": 54.3 }, { "rank": 6, "permaslug": "meta/muse-wonder-20261012", "catalog_id": "meta/muse-wonder", "name": "Muse Wonder (max)", "value": 1232, "win_rate": 50.2 }, { "rank": 7, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 1217, "win_rate": 50.7 }, { "rank": 8, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 1199, "win_rate": 56.5 }, { "rank": 9, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 1191, "win_rate": 50 }, { "rank": 10, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 1189, "win_rate": 49 }, { "rank": 11, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1182, "win_rate": 52.1 }, { "rank": 12, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 1179, "win_rate": 53.1 }, { "rank": 13, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 1165, "win_rate": 52.2 }, { "rank": 14, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 1162, "win_rate": 48.6 }, { "rank": 15, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 1102, "win_rate": 43.8 }, { "rank": 16, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 1094, "win_rate": 40.9 }, { "rank": 17, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 1083, "win_rate": 40.3 }, { "rank": 18, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 1061, "win_rate": 36.2 }, { "rank": 19, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 1046, "win_rate": 36 }, { "rank": 20, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1001, "win_rate": 30.9 }, { "rank": 21, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 767, "win_rate": 9.6 } ], "id": "da-agents-blender3d", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 114 }, { "ranked_count": 21, "scored_count": 21, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 1326, "win_rate": 57.2 }, { "rank": 2, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 1315, "win_rate": 61.8 }, { "rank": 3, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 Max", "value": 1312, "win_rate": 60.8 }, { "rank": 4, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 1306, "win_rate": 57.3 }, { "rank": 5, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 1295, "win_rate": 56.2 }, { "rank": 6, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 1280, "win_rate": 58.2 }, { "rank": 7, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 1264, "win_rate": 54.9 }, { "rank": 8, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1249, "win_rate": 55.3 }, { "rank": 9, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 1249, "win_rate": 53.7 }, { "rank": 10, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 1249, "win_rate": 60.7 }, { "rank": 11, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 1244, "win_rate": 48.1 }, { "rank": 12, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 1241, "win_rate": 60.5 }, { "rank": 13, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 1210, "win_rate": 48 }, { "rank": 14, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 1208, "win_rate": 43.5 }, { "rank": 15, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 1199, "win_rate": 45.4 }, { "rank": 16, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1197, "win_rate": 56.2 }, { "rank": 17, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 1197, "win_rate": 47.2 }, { "rank": 18, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 1191, "win_rate": 47.7 }, { "rank": 19, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 1181, "win_rate": 44.3 }, { "rank": 20, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 1175, "win_rate": 50.9 }, { "rank": 21, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 1006, "win_rate": 28.1 } ], "id": "da-agents-fullstack", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 115 }, { "ranked_count": 17, "scored_count": 17, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 1327, "win_rate": 60.7 }, { "rank": 2, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 1292, "win_rate": 64.3 }, { "rank": 3, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 1279, "win_rate": 54.2 }, { "rank": 4, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 1276, "win_rate": 53 }, { "rank": 5, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 1273, "win_rate": 53 }, { "rank": 6, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 1264, "win_rate": 50.8 }, { "rank": 7, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 Max", "value": 1241, "win_rate": 45.8 }, { "rank": 8, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1231, "win_rate": 55.8 }, { "rank": 9, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 1229, "win_rate": 58.2 }, { "rank": 10, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 1225, "win_rate": 54.4 }, { "rank": 11, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 1223, "win_rate": 48.2 }, { "rank": 12, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 1187, "win_rate": 55.7 }, { "rank": 13, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 1147, "win_rate": 49.2 }, { "rank": 14, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 1142, "win_rate": 40.1 }, { "rank": 15, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 1103, "win_rate": 39.8 }, { "rank": 16, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1098, "win_rate": 43 }, { "rank": 17, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 914, "win_rate": 20.7 } ], "id": "da-agents-godotgamedev", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 118 }, { "ranked_count": 18, "scored_count": 18, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 1394, "win_rate": 56.5 }, { "rank": 2, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3", "value": 1189, "win_rate": 39.1 }, { "rank": 3, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 1173, "win_rate": 63.1 }, { "rank": 4, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 1153, "win_rate": 55.6 }, { "rank": 5, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 1146, "win_rate": 60.1 }, { "rank": 6, "permaslug": "meta/muse-wonder-20261012", "catalog_id": "meta/muse-wonder", "name": "Muse Wonder (max)", "value": 1133, "win_rate": 13.9 }, { "rank": 7, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1117, "win_rate": 58 }, { "rank": 8, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 1114, "win_rate": 53.7 }, { "rank": 9, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 1101, "win_rate": 52.5 }, { "rank": 10, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 1097, "win_rate": 53.6 }, { "rank": 11, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 1091, "win_rate": 51.8 }, { "rank": 12, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 1076, "win_rate": 46.7 }, { "rank": 13, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 1071, "win_rate": 49.5 }, { "rank": 14, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 1054, "win_rate": 43.6 }, { "rank": 15, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 1045, "win_rate": 41.9 }, { "rank": 16, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1039, "win_rate": 46.5 }, { "rank": 17, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 1031, "win_rate": 40 }, { "rank": 18, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 905, "win_rate": 28.4 } ], "id": "da-agents-htmlslides", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 117 }, { "ranked_count": 25, "scored_count": 25, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 1348, "win_rate": 67.1 }, { "rank": 2, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Claude Opus 5.5", "value": 1304, "win_rate": 61.8 }, { "rank": 3, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Claude Sonnet 5.5", "value": 1281, "win_rate": 59.6 }, { "rank": 4, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 1266, "win_rate": 57.4 }, { "rank": 5, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 1265, "win_rate": 56.3 }, { "rank": 6, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 1262, "win_rate": 60.4 }, { "rank": 7, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "value": 1237, "win_rate": 53.3 }, { "rank": 8, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 1236, "win_rate": 54.6 }, { "rank": 9, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 1230, "win_rate": 55.3 }, { "rank": 10, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 1228, "win_rate": 52.3 }, { "rank": 11, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 Max", "value": 1222, "win_rate": 50.2 }, { "rank": 12, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1220, "win_rate": 54.8 }, { "rank": 13, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 1218, "win_rate": 52.4 }, { "rank": 14, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 1216, "win_rate": 48.4 }, { "rank": 15, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 1211, "win_rate": 50.8 }, { "rank": 16, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 1196, "win_rate": 49.9 }, { "rank": 17, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3", "value": 1192, "win_rate": 52.2 }, { "rank": 18, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 1181, "win_rate": 47.7 }, { "rank": 19, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1175, "win_rate": 50.8 }, { "rank": 20, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 1172, "win_rate": 46 }, { "rank": 21, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 1167, "win_rate": 45.7 }, { "rank": 22, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 1161, "win_rate": 48 }, { "rank": 23, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 1157, "win_rate": 45.3 }, { "rank": 24, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 1141, "win_rate": 46.2 }, { "rank": 25, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 1058, "win_rate": 33.4 } ], "id": "da-agents-mobileapps", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 111 }, { "ranked_count": 3, "scored_count": 3, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1306, "win_rate": 67.9 }, { "rank": 2, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1244, "win_rate": 57.7 }, { "rank": 3, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 1071, "win_rate": 32.5 } ], "id": "da-agents-pptxslides", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 132 }, { "ranked_count": 24, "scored_count": 24, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 1318, "win_rate": 60.8 }, { "rank": 2, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1298, "win_rate": 65.9 }, { "rank": 3, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 1250, "win_rate": 61.4 }, { "rank": 4, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1247, "win_rate": 57.4 }, { "rank": 5, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 1222, "win_rate": 54.4 }, { "rank": 6, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 1219, "win_rate": 54.8 }, { "rank": 7, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "GLM-5.3", "value": 1214, "win_rate": 51.2 }, { "rank": 8, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 1201, "win_rate": 51.4 }, { "rank": 9, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 1197, "win_rate": 52.7 }, { "rank": 10, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 1186, "win_rate": 54.1 }, { "rank": 11, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1182, "win_rate": 52.1 }, { "rank": 12, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 1171, "win_rate": 50.1 }, { "rank": 13, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 1159, "win_rate": 47 }, { "rank": 14, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 1150, "win_rate": 48.5 }, { "rank": 15, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 1147, "win_rate": 47.5 }, { "rank": 16, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 1146, "win_rate": 48.6 }, { "rank": 17, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 1137, "win_rate": 40.1 }, { "rank": 18, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1134, "win_rate": 56.9 }, { "rank": 19, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 1112, "win_rate": 44.4 }, { "rank": 20, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 1108, "win_rate": 44.6 }, { "rank": 21, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 1096, "win_rate": 38.8 }, { "rank": 22, "permaslug": "meta/muse-wonder-20261012", "catalog_id": "meta/muse-wonder", "name": "Muse Wonder (max)", "value": 1096, "win_rate": 14.2 }, { "rank": 23, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 1072, "win_rate": 30.8 }, { "rank": 24, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 967, "win_rate": 29.1 } ], "id": "da-agents-python-pptxslides", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 114 }, { "ranked_count": 21, "scored_count": 21, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 1414, "win_rate": 70.4 }, { "rank": 2, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Claude Opus 5.5", "value": 1392, "win_rate": 69.3 }, { "rank": 3, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Claude Sonnet 5.5", "value": 1287, "win_rate": 53.3 }, { "rank": 4, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "value": 1284, "win_rate": 52.5 }, { "rank": 5, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek-V4.1-Flash (1017)", "value": 1278, "win_rate": 51.2 }, { "rank": 6, "permaslug": "meta/muse-wonder-20261012", "catalog_id": "meta/muse-wonder", "name": "Muse Wonder (max)", "value": 1277, "win_rate": 49.7 }, { "rank": 7, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1240, "win_rate": 68 }, { "rank": 8, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Gemini 4 Argon", "value": 1189, "win_rate": 32.8 }, { "rank": 9, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 1158, "win_rate": 52.4 }, { "rank": 10, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 1114, "win_rate": 32.4 }, { "rank": 11, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 1110, "win_rate": 46.9 }, { "rank": 12, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 1097, "win_rate": 47.1 }, { "rank": 13, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 1092, "win_rate": 29.9 }, { "rank": 14, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 1083, "win_rate": 45 }, { "rank": 15, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 1079, "win_rate": 45.6 }, { "rank": 16, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1077, "win_rate": 43.5 }, { "rank": 17, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 1077, "win_rate": 45 }, { "rank": 18, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 1051, "win_rate": 40.5 }, { "rank": 19, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 1051, "win_rate": 46.1 }, { "rank": 20, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 1034, "win_rate": 35.3 }, { "rank": 21, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 921, "win_rate": 34.5 } ], "id": "da-agents-spreadsheet", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 114 }, { "ranked_count": 27, "scored_count": 27, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Claude Opus 5.5", "value": 1319, "win_rate": 61.1 }, { "rank": 2, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Claude Fable 5.1", "value": 1318, "win_rate": 56.1 }, { "rank": 3, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Claude Sonnet 5.5", "value": 1305, "win_rate": 60.3 }, { "rank": 4, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "value": 1305, "win_rate": 60 }, { "rank": 5, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 (xhigh)", "value": 1297, "win_rate": 56.6 }, { "rank": 6, "permaslug": "meta/muse-spark-1.3-20260902", "catalog_id": "meta/muse-spark-1.3", "name": "Muse Spark 1.3 Max", "value": 1297, "win_rate": 54.9 }, { "rank": 7, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "Kimi K3", "value": 1295, "win_rate": 59.3 }, { "rank": 8, "permaslug": "xiaomi/mimo-v2.6-pro-20260921", "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "MiMo-V2.6-Pro", "value": 1290, "win_rate": 58.3 }, { "rank": 9, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 1266, "win_rate": 54.3 }, { "rank": 10, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Claude Fable 5", "value": 1261, "win_rate": 56.3 }, { "rank": 11, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "Grok 4.6", "value": 1248, "win_rate": 55.8 }, { "rank": 12, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "value": 1244, "win_rate": 53 }, { "rank": 13, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 1239, "win_rate": 46.9 }, { "rank": 14, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Claude Opus 4.8", "value": 1233, "win_rate": 51.4 }, { "rank": 15, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Gemini 3.7 Flash", "value": 1222, "win_rate": 47.1 }, { "rank": 16, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "GLM 5.2", "value": 1222, "win_rate": 55.8 }, { "rank": 17, "permaslug": "meta/muse-spark-1.2-20260805", "catalog_id": "meta/muse-spark-1.2", "name": "Muse Spark 1.2", "value": 1221, "win_rate": 50.2 }, { "rank": 18, "permaslug": "x-ai/grok-4.5-20260708", "catalog_id": "x-ai/grok-4.5", "name": "Grok 4.5", "value": 1218, "win_rate": 53.4 }, { "rank": 19, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen3.7 Max", "value": 1208, "win_rate": 48.8 }, { "rank": 20, "permaslug": "meta/muse-spark-1.1-20260709", "catalog_id": "meta/muse-spark-1.1", "name": "Muse Spark 1.1", "value": 1207, "win_rate": 49.1 }, { "rank": 21, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Gemini 3.5 Flash", "value": 1202, "win_rate": 52.2 }, { "rank": 22, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax M3", "value": 1201, "win_rate": 47.1 }, { "rank": 23, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Gemini 3.6 Flash", "value": 1197, "win_rate": 45.6 }, { "rank": 24, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Inkling", "value": 1196, "win_rate": 48.6 }, { "rank": 25, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "Kimi K2.7 Code", "value": 1176, "win_rate": 46.9 }, { "rank": 26, "permaslug": "x-ai/grok-4.3-20260430", "catalog_id": "x-ai/grok-4.3", "name": "Grok 4.3", "value": 1126, "win_rate": 42.8 }, { "rank": 27, "permaslug": "upstage/solar-pro4-20260810", "catalog_id": "upstage/solar-pro4", "name": "Solar Pro 4", "value": 1105, "win_rate": 30 } ], "id": "da-agents-webapps", "source": "design-arena", "group": "quality", "field": "elo", "direction": "higher_better", "missing_in_window": 109 }, { "ranked_count": 77, "scored_count": 77, "truncated": false, "rows": [ { "rank": 1, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Google: Gemini 4 Argon", "value": 0.964646, "total_tasks": 198 }, { "rank": 2, "permaslug": "google/gemini-4-argon", "catalog_id": "google/gemini-4-argon", "name": "Gemini 4 Argon", "value": 0.959596, "total_tasks": 198 }, { "rank": 3, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Google: Gemini 3.8 Flash", "value": 0.95637, "total_tasks": 191 }, { "rank": 4, "permaslug": "openai/gpt-6-astra-pro-20260903", "catalog_id": "openai/gpt-6-astra-pro", "name": "OpenAI: GPT-6 Astra Pro", "value": 0.954545, "total_tasks": 198 }, { "rank": 5, "permaslug": "sakana/fugu-ultra", "catalog_id": "sakana/fugu-ultra", "name": "Fugu Ultra", "value": 0.9461279999999999, "total_tasks": 198 }, { "rank": 6, "permaslug": "openai/gpt-6-astra-20260903", "catalog_id": "openai/gpt-6-astra", "name": "OpenAI: GPT-6 Astra", "value": 0.944444, "total_tasks": 198 }, { "rank": 7, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "OpenAI: GPT-6.1 Sol", "value": 0.944444, "total_tasks": 198 }, { "rank": 8, "permaslug": "openai/gpt-5.6-sol-pro-20260709", "catalog_id": "openai/gpt-5.6-sol-pro", "name": "OpenAI: GPT-5.6 Sol Pro", "value": 0.9393935, "total_tasks": 396 }, { "rank": 9, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Google: Gemini 3.7 Flash", "value": 0.938528, "total_tasks": 385 }, { "rank": 10, "permaslug": "google/gemini-3.8-flash", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 0.9343430000000001, "total_tasks": 198 }, { "rank": 11, "permaslug": "sakana/fugu-ultra-v2", "catalog_id": "sakana/fugu-ultra-v2", "name": "Fugu Ultra V2", "value": 0.93266, "total_tasks": 198 }, { "rank": 12, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "SpaceXAI: Grok 4.6", "value": 0.928451, "total_tasks": 396 }, { "rank": 13, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Anthropic: Claude Sonnet 5.5", "value": 0.9271882499999999, "total_tasks": 792 }, { "rank": 14, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Google: Gemini 3.6 Flash", "value": 0.9264870000000001, "total_tasks": 594 }, { "rank": 15, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Google: Gemini 3.5 Flash", "value": 0.9259256666666668, "total_tasks": 594 }, { "rank": 16, "permaslug": "openai/gpt-5.6-sol-20260709", "catalog_id": "openai/gpt-5.6-sol", "name": "OpenAI: GPT-5.6 Sol", "value": 0.9208750000000001, "total_tasks": 594 }, { "rank": 17, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "MoonshotAI: Kimi K3", "value": 0.9194090050632909, "total_tasks": 2370 }, { "rank": 18, "permaslug": "openai/gpt-6-sol-20260922", "catalog_id": "openai/gpt-6-sol", "name": "OpenAI: GPT-6 Sol", "value": 0.9191919999999999, "total_tasks": 198 }, { "rank": 19, "permaslug": "openai/gpt-6.1-terra", "catalog_id": "openai/gpt-6.1-terra", "name": "GPT-6.1-Terra", "value": 0.9141410000000001, "total_tasks": 198 }, { "rank": 20, "permaslug": "z-ai/glm-5.3-flash", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM 5.3 Flash", "value": 0.9090909999999999, "total_tasks": 198 }, { "rank": 21, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen: Qwen3.7 Max", "value": 0.9090909999999999, "total_tasks": 198 }, { "rank": 22, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek: DeepSeek V4.1 Flash 1017", "value": 0.907407, "total_tasks": 198 }, { "rank": 23, "permaslug": "nvidia/switchyard", "catalog_id": "nvidia/switchyard", "name": "NVIDIA: Switchyard", "value": 0.9071381724573594, "total_tasks": 1583 }, { "rank": 24, "permaslug": "meta/muse-spark-open-20261015", "catalog_id": "meta/muse-spark-open", "name": "Meta: Muse Spark Open", "value": 0.905724, "total_tasks": 198 }, { "rank": 25, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax: MiniMax M3", "value": 0.9047062578763128, "total_tasks": 2571 }, { "rank": 26, "permaslug": "moonshotai/kimi-k3.1-pro", "catalog_id": "moonshotai/kimi-k3.1-pro", "name": "Kimi K3.1 Pro", "value": 0.9040400000000001, "total_tasks": 198 }, { "rank": 27, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Anthropic: Claude Opus 5.5", "value": 0.9023568, "total_tasks": 990 }, { "rank": 28, "permaslug": "deepseek/deepseek-v4-pro-20260813", "catalog_id": "deepseek/deepseek-v4-pro-0813", "name": "DeepSeek: DeepSeek V4 Pro 0813", "value": 0.9016089931034483, "total_tasks": 2175 }, { "rank": 29, "permaslug": "deepseek/deepseek-v4.1-flash-1017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "Deepseek V4.1 Flash 1017", "value": 0.901515, "total_tasks": 198 }, { "rank": 30, "permaslug": "openai/gpt-5.6-luna-pro-20260709", "catalog_id": "openai/gpt-5.6-luna-pro", "name": "OpenAI: GPT-5.6 Luna Pro", "value": 0.899551, "total_tasks": 594 }, { "rank": 31, "permaslug": "tencent/hy4-preview-20260827", "catalog_id": "tencent/hy4-preview", "name": "Tencent: Hy4 preview", "value": 0.8995506666666668, "total_tasks": 594 }, { "rank": 32, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Anthropic: Claude Fable 5.1", "value": 0.8993264, "total_tasks": 990 }, { "rank": 33, "permaslug": "openai/gpt-6-luna", "catalog_id": "openai/gpt-6-luna", "name": "GPT-6-Luna", "value": 0.898477, "total_tasks": 197 }, { "rank": 34, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Anthropic: Claude Opus 4.8", "value": 0.8971659166666668, "total_tasks": 2376 }, { "rank": 35, "permaslug": "deepseek/deepseek-v4.1-flash-20260910", "catalog_id": "deepseek/deepseek-v4.1-flash", "name": "DeepSeek: DeepSeek V4.1 Flash", "value": 0.8919751666666667, "total_tasks": 1188 }, { "rank": 36, "permaslug": "openai/gpt-5.6-terra-20260709", "catalog_id": "openai/gpt-5.6-terra", "name": "OpenAI: GPT-5.6 Terra", "value": 0.8877663333333334, "total_tasks": 594 }, { "rank": 37, "permaslug": "xiaomi/mimo-v2.6-pro-20260921", "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "Xiaomi: MiMo-V2.6-Pro", "value": 0.8867541405460061, "total_tasks": 989 }, { "rank": 38, "permaslug": "sakana/fugu-max", "catalog_id": "sakana/fugu-max", "name": "Fugu Max", "value": 0.885522, "total_tasks": 198 }, { "rank": 39, "permaslug": "qwen/qwen3.8-flash-20260826", "catalog_id": "qwen/qwen3.8-flash", "name": "Qwen: Qwen3.8 Flash", "value": 0.885522, "total_tasks": 198 }, { "rank": 40, "permaslug": "openai/gpt-6-luna-pro-20260922", "catalog_id": "openai/gpt-6-luna-pro", "name": "OpenAI: GPT-6 Luna Pro", "value": 0.883838, "total_tasks": 198 }, { "rank": 41, "permaslug": "reflection/beam-1.0-501b-a23b-20261016", "catalog_id": "reflection/beam-1.0-501b-a23b", "name": "Reflection: Beam 1.0 501B A23B", "value": 0.883838, "total_tasks": 198 }, { "rank": 42, "permaslug": "deepseek/deepseek-v4-flash-vision-exp-20260821", "catalog_id": "deepseek/deepseek-v4-flash-vision-exp", "name": "DeepSeek: DeepSeek V4 Flash Vision Exp", "value": 0.8801906666666667, "total_tasks": 1188 }, { "rank": 43, "permaslug": "deepseek/deepseek-v4.1-flash", "catalog_id": "deepseek/deepseek-v4.1-flash", "name": "Deepseek V4.1 Flash", "value": 0.878788, "total_tasks": 198 }, { "rank": 44, "permaslug": "xiaomi/mimo-v2.6-pro", "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "Mimo V2.6 Pro", "value": 0.878788, "total_tasks": 198 }, { "rank": 45, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen: Qwen3.7 Plus", "value": 0.878788, "total_tasks": 198 }, { "rank": 46, "permaslug": "openai/gpt-5.6-luna-20260709", "catalog_id": "openai/gpt-5.6-luna", "name": "OpenAI: GPT-5.6 Luna", "value": 0.8787876666666666, "total_tasks": 594 }, { "rank": 47, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Anthropic: Claude Opus 5", "value": 0.87780575, "total_tasks": 2376 }, { "rank": 48, "permaslug": "nvidia/nemotron-3.5-super-vl-20261015", "catalog_id": "nvidia/nemotron-3.5-super-vl", "name": "NVIDIA: Nemotron 3.5 Super VL", "value": 0.8737370000000001, "total_tasks": 396 }, { "rank": 49, "permaslug": "openai/gpt-6-luna-20260922", "catalog_id": "openai/gpt-6-luna", "name": "OpenAI: GPT-6 Luna", "value": 0.873737, "total_tasks": 198 }, { "rank": 50, "permaslug": "qwen/qwen3.8-2.4t-a95b-20260812", "catalog_id": "qwen/qwen3.8-2.4t-a95b", "name": "Qwen: Qwen3.8 2.4T A95B", "value": 0.8713054444444444, "total_tasks": 1782 }, { "rank": 51, "permaslug": "anthropic/claude-haiku-5.5-20261007", "catalog_id": "anthropic/claude-haiku-5.5", "name": "Anthropic: Claude Haiku 5.5", "value": 0.8686866666666666, "total_tasks": 594 }, { "rank": 52, "permaslug": "minimax/minimax-m3.1-flash-20261019", "catalog_id": "minimax/minimax-m3.1-flash", "name": "MiniMax: MiniMax M3.1 Flash", "value": 0.867003, "total_tasks": 198 }, { "rank": 53, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek: DeepSeek V4 Flash 0731", "value": 0.8666971818181819, "total_tasks": 2178 }, { "rank": 54, "permaslug": "thinkingmachines/inkling-small-20260730", "catalog_id": "thinkingmachines/inkling-small", "name": "Thinking Machines: Inkling Small", "value": 0.8656005, "total_tasks": 1188 }, { "rank": 55, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Anthropic: Claude Fable 5", "value": 0.8638953076923075, "total_tasks": 2574 }, { "rank": 56, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "MoonshotAI: Kimi K2.7 Code", "value": 0.8619528181818182, "total_tasks": 2178 }, { "rank": 57, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "Z.ai: GLM 5.3", "value": 0.8524129999999999, "total_tasks": 1782 }, { "rank": 58, "permaslug": "inclusionai/ling-3.0-flash-vl-20260910", "catalog_id": "inclusionai/ling-3.0-flash-vl", "name": "inclusionAI: Ling 3.0 Flash VL", "value": 0.848485, "total_tasks": 198 }, { "rank": 59, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "Z.ai: GLM 5.2", "value": 0.84771325, "total_tasks": 2376 }, { "rank": 60, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Anthropic: Claude Sonnet 5", "value": 0.8474003453908985, "total_tasks": 2571 }, { "rank": 61, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "Z.ai: GLM 5.3 Flash", "value": 0.8441825555555555, "total_tasks": 1782 }, { "rank": 62, "permaslug": "google/gemini-3.5-flash-lite-20260721", "catalog_id": "google/gemini-3.5-flash-lite", "name": "Google: Gemini 3.5 Flash Lite", "value": 0.8411896666666667, "total_tasks": 594 }, { "rank": 63, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Thinking Machines: Inkling", "value": 0.8340364430379746, "total_tasks": 1185 }, { "rank": 64, "permaslug": "qwen/qwen3.6-27b-20260422", "catalog_id": "qwen/qwen3.6-27b", "name": "Qwen: Qwen3.6 27B", "value": 0.8252562970922881, "total_tasks": 2373 }, { "rank": 65, "permaslug": "z-ai/glm-5.3", "catalog_id": "z-ai/glm-5.3", "name": "GLM 5.3", "value": 0.823232, "total_tasks": 198 }, { "rank": 66, "permaslug": "qwen/qwen3.8-27b-20260814", "catalog_id": "qwen/qwen3.8-27b", "name": "Qwen: Qwen3.8 27B", "value": 0.8183501, "total_tasks": 1980 }, { "rank": 67, "permaslug": "google/gemini-3.1-flash-lite-20260507", "catalog_id": "google/gemini-3.1-flash-lite", "name": "Google: Gemini 3.1 Flash Lite", "value": 0.815937, "total_tasks": 594 }, { "rank": 68, "permaslug": "inclusionai/ling-3.1-flash-20261002", "catalog_id": "inclusionai/ling-3.1-flash", "name": "inclusionAI: Ling 3.1 Flash", "value": 0.813051, "total_tasks": 189 }, { "rank": 69, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "NVIDIA: Nemotron 3 Ultra", "value": 0.812016, "total_tasks": 172 }, { "rank": 70, "permaslug": "meta/muse-glimmer-30b-20260810", "catalog_id": "meta/muse-glimmer-30b", "name": "Meta: Muse Glimmer 30B", "value": 0.8059763749999999, "total_tasks": 1584 }, { "rank": 71, "permaslug": "qwen/qwen3.6-35b-a3b-20260415", "catalog_id": "qwen/qwen3.6-35b-a3b", "name": "Qwen: Qwen3.6 35B A3B", "value": 0.7944022499999999, "total_tasks": 2376 }, { "rank": 72, "permaslug": "inclusionai/ling-3.0-flash-20260723", "catalog_id": "inclusionai/ling-3.0-flash", "name": "inclusionAI: Ling 3.0 Flash", "value": 0.7487311624365482, "total_tasks": 394 }, { "rank": 73, "permaslug": "xiaomi/mimo-v2.6-flash-20260921", "catalog_id": "xiaomi/mimo-v2.6-flash", "name": "Xiaomi: MiMo-V2.6-Flash", "value": 0.742214, "total_tasks": 792 }, { "rank": 74, "permaslug": "nvidia/nemotron-3.5-lightning-20260807", "catalog_id": "nvidia/nemotron-3.5-lightning", "name": "NVIDIA: Nemotron 3.5 Lightning", "value": 0.7030114672897196, "total_tasks": 1926 }, { "rank": 75, "permaslug": "ibm-granite/granite-4.2-8b-20260831", "catalog_id": "ibm-granite/granite-4.2-8b", "name": "IBM: Granite 4.2 8B", "value": 0.65736, "total_tasks": 197 }, { "rank": 76, "permaslug": "tencent/hy-mt2-30b-a3b-20260521", "catalog_id": "tencent/hy-mt2-30b-a3b", "name": "Tencent: Hy-MT2-30B-A3B", "value": 0.388889, "total_tasks": 198 }, { "rank": 77, "permaslug": "google/gemini-3.1-flash-lite-image-20260630", "catalog_id": "google/gemini-3.1-flash-lite-image", "name": "Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)", "value": 0.102694, "total_tasks": 396 } ], "id": "or-gpqa_diamond", "source": "openrouter", "group": "quality", "field": "accuracy", "direction": "higher_better", "missing_in_window": 66 }, { "ranked_count": 77, "scored_count": 77, "truncated": false, "rows": [ { "rank": 1, "permaslug": "tencent/hy-mt2-30b-a3b-20260521", "catalog_id": "tencent/hy-mt2-30b-a3b", "name": "Tencent: Hy-MT2-30B-A3B", "value": 0.00023147979797979797, "total_tasks": 198 }, { "rank": 2, "permaslug": "inclusionai/ling-3.0-flash-vl-20260910", "catalog_id": "inclusionai/ling-3.0-flash-vl", "name": "inclusionAI: Ling 3.0 Flash VL", "value": 0.0012582575757575758, "total_tasks": 198 }, { "rank": 3, "permaslug": "inclusionai/ling-3.0-flash-20260723", "catalog_id": "inclusionai/ling-3.0-flash", "name": "inclusionAI: Ling 3.0 Flash", "value": 0.00260698730964467, "total_tasks": 394 }, { "rank": 4, "permaslug": "openai/gpt-6-luna-20260922", "catalog_id": "openai/gpt-6-luna", "name": "OpenAI: GPT-6 Luna", "value": 0.0029526111111111116, "total_tasks": 198 }, { "rank": 5, "permaslug": "openai/gpt-6-luna", "catalog_id": "openai/gpt-6-luna", "name": "GPT-6-Luna", "value": 0.003442197969543147, "total_tasks": 197 }, { "rank": 6, "permaslug": "anthropic/claude-haiku-5.5-20261007", "catalog_id": "anthropic/claude-haiku-5.5", "name": "Anthropic: Claude Haiku 5.5", "value": 0.004029786195286195, "total_tasks": 594 }, { "rank": 7, "permaslug": "z-ai/glm-5.3-flash", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM 5.3 Flash", "value": 0.0054125, "total_tasks": 198 }, { "rank": 8, "permaslug": "deepseek/deepseek-v4.1-flash-1017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "Deepseek V4.1 Flash 1017", "value": 0.006598151515151515, "total_tasks": 198 }, { "rank": 9, "permaslug": "openai/gpt-6.1-terra", "catalog_id": "openai/gpt-6.1-terra", "name": "GPT-6.1-Terra", "value": 0.0075055656565656565, "total_tasks": 198 }, { "rank": 10, "permaslug": "inclusionai/ling-3.1-flash-20261002", "catalog_id": "inclusionai/ling-3.1-flash", "name": "inclusionAI: Ling 3.1 Flash", "value": 0.00766168253968254, "total_tasks": 189 }, { "rank": 11, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek: DeepSeek V4 Flash 0731", "value": 0.007686401744719926, "total_tasks": 2178 }, { "rank": 12, "permaslug": "openai/gpt-5.6-luna-20260709", "catalog_id": "openai/gpt-5.6-luna", "name": "OpenAI: GPT-5.6 Luna", "value": 0.007907055555555554, "total_tasks": 594 }, { "rank": 13, "permaslug": "openai/gpt-6-luna-pro-20260922", "catalog_id": "openai/gpt-6-luna-pro", "name": "OpenAI: GPT-6 Luna Pro", "value": 0.008301368686868687, "total_tasks": 198 }, { "rank": 14, "permaslug": "nvidia/nemotron-3.5-lightning-20260807", "catalog_id": "nvidia/nemotron-3.5-lightning", "name": "NVIDIA: Nemotron 3.5 Lightning", "value": 0.009145764278296989, "total_tasks": 1926 }, { "rank": 15, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek: DeepSeek V4.1 Flash 1017", "value": 0.010421979797979798, "total_tasks": 198 }, { "rank": 16, "permaslug": "deepseek/deepseek-v4.1-flash", "catalog_id": "deepseek/deepseek-v4.1-flash", "name": "Deepseek V4.1 Flash", "value": 0.010643959595959596, "total_tasks": 198 }, { "rank": 17, "permaslug": "xiaomi/mimo-v2.6-pro", "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "Mimo V2.6 Pro", "value": 0.01249009595959596, "total_tasks": 198 }, { "rank": 18, "permaslug": "minimax/minimax-m3.1-flash-20261019", "catalog_id": "minimax/minimax-m3.1-flash", "name": "MiniMax: MiniMax M3.1 Flash", "value": 0.013525050505050505, "total_tasks": 198 }, { "rank": 19, "permaslug": "reflection/beam-1.0-501b-a23b-20261016", "catalog_id": "reflection/beam-1.0-501b-a23b", "name": "Reflection: Beam 1.0 501B A23B", "value": 0.014282979797979798, "total_tasks": 198 }, { "rank": 20, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "Z.ai: GLM 5.3 Flash", "value": 0.014299253647586982, "total_tasks": 1782 }, { "rank": 21, "permaslug": "ibm-granite/granite-4.2-8b-20260831", "catalog_id": "ibm-granite/granite-4.2-8b", "name": "IBM: Granite 4.2 8B", "value": 0.014864365482233502, "total_tasks": 197 }, { "rank": 22, "permaslug": "nvidia/switchyard", "catalog_id": "nvidia/switchyard", "name": "NVIDIA: Switchyard", "value": 0.015826173089071385, "total_tasks": 1583 }, { "rank": 23, "permaslug": "xiaomi/mimo-v2.6-flash-20260921", "catalog_id": "xiaomi/mimo-v2.6-flash", "name": "Xiaomi: MiMo-V2.6-Flash", "value": 0.01671199116161616, "total_tasks": 792 }, { "rank": 24, "permaslug": "google/gemini-3.1-flash-lite-image-20260630", "catalog_id": "google/gemini-3.1-flash-lite-image", "name": "Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)", "value": 0.017984406565656568, "total_tasks": 396 }, { "rank": 25, "permaslug": "moonshotai/kimi-k3.1-pro", "catalog_id": "moonshotai/kimi-k3.1-pro", "name": "Kimi K3.1 Pro", "value": 0.021051848484848486, "total_tasks": 198 }, { "rank": 26, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "OpenAI: GPT-6.1 Sol", "value": 0.02136650505050505, "total_tasks": 198 }, { "rank": 27, "permaslug": "qwen/qwen3.8-flash-20260826", "catalog_id": "qwen/qwen3.8-flash", "name": "Qwen: Qwen3.8 Flash", "value": 0.02146120202020202, "total_tasks": 198 }, { "rank": 28, "permaslug": "meta/muse-glimmer-30b-20260810", "catalog_id": "meta/muse-glimmer-30b", "name": "Meta: Muse Glimmer 30B", "value": 0.022531703914141412, "total_tasks": 1584 }, { "rank": 29, "permaslug": "deepseek/deepseek-v4-flash-vision-exp-20260821", "catalog_id": "deepseek/deepseek-v4-flash-vision-exp", "name": "DeepSeek: DeepSeek V4 Flash Vision Exp", "value": 0.0227881835016835, "total_tasks": 1188 }, { "rank": 30, "permaslug": "nvidia/nemotron-3.5-super-vl-20261015", "catalog_id": "nvidia/nemotron-3.5-super-vl", "name": "NVIDIA: Nemotron 3.5 Super VL", "value": 0.023037462121212122, "total_tasks": 396 }, { "rank": 31, "permaslug": "google/gemini-3.8-flash", "catalog_id": "google/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "value": 0.023175040404040403, "total_tasks": 198 }, { "rank": 32, "permaslug": "deepseek/deepseek-v4.1-flash-20260910", "catalog_id": "deepseek/deepseek-v4.1-flash", "name": "DeepSeek: DeepSeek V4.1 Flash", "value": 0.024034642255892257, "total_tasks": 1188 }, { "rank": 33, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Anthropic: Claude Sonnet 5.5", "value": 0.025096623737373737, "total_tasks": 792 }, { "rank": 34, "permaslug": "thinkingmachines/inkling-small-20260730", "catalog_id": "thinkingmachines/inkling-small", "name": "Thinking Machines: Inkling Small", "value": 0.02525451262626263, "total_tasks": 1188 }, { "rank": 35, "permaslug": "openai/gpt-6-sol-20260922", "catalog_id": "openai/gpt-6-sol", "name": "OpenAI: GPT-6 Sol", "value": 0.02528019191919192, "total_tasks": 198 }, { "rank": 36, "permaslug": "z-ai/glm-5.3", "catalog_id": "z-ai/glm-5.3", "name": "GLM 5.3", "value": 0.025912994949494946, "total_tasks": 198 }, { "rank": 37, "permaslug": "google/gemini-4-argon", "catalog_id": "google/gemini-4-argon", "name": "Gemini 4 Argon", "value": 0.029260161616161615, "total_tasks": 198 }, { "rank": 38, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Google: Gemini 3.7 Flash", "value": 0.0293307974025974, "total_tasks": 385 }, { "rank": 39, "permaslug": "xiaomi/mimo-v2.6-pro-20260921", "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "Xiaomi: MiMo-V2.6-Pro", "value": 0.03347630637007078, "total_tasks": 989 }, { "rank": 40, "permaslug": "qwen/qwen3.8-27b-20260814", "catalog_id": "qwen/qwen3.8-27b", "name": "Qwen: Qwen3.8 27B", "value": 0.033925831313131316, "total_tasks": 1980 }, { "rank": 41, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax: MiniMax M3", "value": 0.03395674834694671, "total_tasks": 2571 }, { "rank": 42, "permaslug": "openai/gpt-5.6-terra-20260709", "catalog_id": "openai/gpt-5.6-terra", "name": "OpenAI: GPT-5.6 Terra", "value": 0.03440870875420875, "total_tasks": 594 }, { "rank": 43, "permaslug": "google/gemini-3.5-flash-lite-20260721", "catalog_id": "google/gemini-3.5-flash-lite", "name": "Google: Gemini 3.5 Flash Lite", "value": 0.036658867003367, "total_tasks": 594 }, { "rank": 44, "permaslug": "openai/gpt-5.6-luna-pro-20260709", "catalog_id": "openai/gpt-5.6-luna-pro", "name": "OpenAI: GPT-5.6 Luna Pro", "value": 0.0412280202020202, "total_tasks": 594 }, { "rank": 45, "permaslug": "google/gemini-3.1-flash-lite-20260507", "catalog_id": "google/gemini-3.1-flash-lite", "name": "Google: Gemini 3.1 Flash Lite", "value": 0.04137441245791246, "total_tasks": 594 }, { "rank": 46, "permaslug": "qwen/qwen3.6-35b-a3b-20260415", "catalog_id": "qwen/qwen3.6-35b-a3b", "name": "Qwen: Qwen3.6 35B A3B", "value": 0.04325068055555555, "total_tasks": 2376 }, { "rank": 47, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen: Qwen3.7 Plus", "value": 0.043995565656565656, "total_tasks": 198 }, { "rank": 48, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Anthropic: Claude Opus 5.5", "value": 0.05410575151515151, "total_tasks": 990 }, { "rank": 49, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Google: Gemini 3.6 Flash", "value": 0.05958464141414141, "total_tasks": 594 }, { "rank": 50, "permaslug": "openai/gpt-5.6-sol-20260709", "catalog_id": "openai/gpt-5.6-sol", "name": "OpenAI: GPT-5.6 Sol", "value": 0.06043574579124578, "total_tasks": 594 }, { "rank": 51, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Google: Gemini 3.8 Flash", "value": 0.06822796858638744, "total_tasks": 191 }, { "rank": 52, "permaslug": "meta/muse-spark-open-20261015", "catalog_id": "meta/muse-spark-open", "name": "Meta: Muse Spark Open", "value": 0.06900820707070707, "total_tasks": 198 }, { "rank": 53, "permaslug": "sakana/fugu-max", "catalog_id": "sakana/fugu-max", "name": "Fugu Max", "value": 0.07555469191919191, "total_tasks": 198 }, { "rank": 54, "permaslug": "qwen/qwen3.8-2.4t-a95b-20260812", "catalog_id": "qwen/qwen3.8-2.4t-a95b", "name": "Qwen: Qwen3.8 2.4T A95B", "value": 0.08585465039281706, "total_tasks": 1782 }, { "rank": 55, "permaslug": "qwen/qwen3.6-27b-20260422", "catalog_id": "qwen/qwen3.6-27b", "name": "Qwen: Qwen3.6 27B", "value": 0.08621131184155077, "total_tasks": 2373 }, { "rank": 56, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Google: Gemini 4 Argon", "value": 0.09468125757575757, "total_tasks": 198 }, { "rank": 57, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Thinking Machines: Inkling", "value": 0.0954248565400844, "total_tasks": 1185 }, { "rank": 58, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "MoonshotAI: Kimi K2.7 Code", "value": 0.09933105968778695, "total_tasks": 2178 }, { "rank": 59, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "Z.ai: GLM 5.3", "value": 0.1049078827160494, "total_tasks": 1782 }, { "rank": 60, "permaslug": "deepseek/deepseek-v4-pro-20260813", "catalog_id": "deepseek/deepseek-v4-pro-0813", "name": "DeepSeek: DeepSeek V4 Pro 0813", "value": 0.10899811586206896, "total_tasks": 2175 }, { "rank": 61, "permaslug": "openai/gpt-6-astra-20260903", "catalog_id": "openai/gpt-6-astra", "name": "OpenAI: GPT-6 Astra", "value": 0.11333201010101009, "total_tasks": 198 }, { "rank": 62, "permaslug": "tencent/hy4-preview-20260827", "catalog_id": "tencent/hy4-preview", "name": "Tencent: Hy4 preview", "value": 0.11900113804713805, "total_tasks": 594 }, { "rank": 63, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "SpaceXAI: Grok 4.6", "value": 0.12326839393939394, "total_tasks": 396 }, { "rank": 64, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "Z.ai: GLM 5.2", "value": 0.12780570496632998, "total_tasks": 2376 }, { "rank": 65, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Anthropic: Claude Opus 5", "value": 0.1286623606902357, "total_tasks": 2376 }, { "rank": 66, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Anthropic: Claude Fable 5.1", "value": 0.13052546969696968, "total_tasks": 990 }, { "rank": 67, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "MoonshotAI: Kimi K3", "value": 0.1314646818565401, "total_tasks": 2370 }, { "rank": 68, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Google: Gemini 3.5 Flash", "value": 0.1413088872053872, "total_tasks": 594 }, { "rank": 69, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "NVIDIA: Nemotron 3 Ultra", "value": 0.14135672674418603, "total_tasks": 172 }, { "rank": 70, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Anthropic: Claude Sonnet 5", "value": 0.16651004745235318, "total_tasks": 2571 }, { "rank": 71, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Anthropic: Claude Fable 5", "value": 0.1779076884226884, "total_tasks": 2574 }, { "rank": 72, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Anthropic: Claude Opus 4.8", "value": 0.19972315109427613, "total_tasks": 2376 }, { "rank": 73, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen: Qwen3.7 Max", "value": 0.2221867676767677, "total_tasks": 198 }, { "rank": 74, "permaslug": "openai/gpt-5.6-sol-pro-20260709", "catalog_id": "openai/gpt-5.6-sol-pro", "name": "OpenAI: GPT-5.6 Sol Pro", "value": 0.29793838636363634, "total_tasks": 396 }, { "rank": 75, "permaslug": "openai/gpt-6-astra-pro-20260903", "catalog_id": "openai/gpt-6-astra-pro", "name": "OpenAI: GPT-6 Astra Pro", "value": 0.332555398989899, "total_tasks": 198 }, { "rank": 76, "permaslug": "sakana/fugu-ultra-v2", "catalog_id": "sakana/fugu-ultra-v2", "name": "Fugu Ultra V2", "value": 0.5025571414141414, "total_tasks": 198 }, { "rank": 77, "permaslug": "sakana/fugu-ultra", "catalog_id": "sakana/fugu-ultra", "name": "Fugu Ultra", "value": 1.148739303030303, "total_tasks": 198 } ], "id": "or-gpqa_diamond-cost", "source": "openrouter", "group": "value", "field": "avg_cost_per_task", "direction": "lower_better", "missing_in_window": 66 }, { "ranked_count": 63, "scored_count": 63, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Anthropic: Claude Fable 5", "value": 0.7994444166666667, "total_tasks": 600 }, { "rank": 2, "permaslug": "inclusionai/ling-3.1-flash-20261002", "catalog_id": "inclusionai/ling-3.1-flash", "name": "inclusionAI: Ling 3.1 Flash", "value": 0.793333, "total_tasks": 50 }, { "rank": 3, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Anthropic: Claude Fable 5.1", "value": 0.79166675, "total_tasks": 200 }, { "rank": 4, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Anthropic: Claude Opus 5", "value": 0.78777775, "total_tasks": 600 }, { "rank": 5, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Google: Gemini 4 Argon", "value": 0.786667, "total_tasks": 50 }, { "rank": 6, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Anthropic: Claude Sonnet 5.5", "value": 0.78666675, "total_tasks": 200 }, { "rank": 7, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Google: Gemini 3.7 Flash", "value": 0.7831052054794521, "total_tasks": 146 }, { "rank": 8, "permaslug": "xiaomi/mimo-v2.6-flash-20260921", "catalog_id": "xiaomi/mimo-v2.6-flash", "name": "Xiaomi: MiMo-V2.6-Flash", "value": 0.78166675, "total_tasks": 200 }, { "rank": 9, "permaslug": "qwen/qwen3.8-27b-20260814", "catalog_id": "qwen/qwen3.8-27b", "name": "Qwen: Qwen3.8 27B", "value": 0.7800001111111111, "total_tasks": 450 }, { "rank": 10, "permaslug": "deepseek/deepseek-v4-pro-20260813", "catalog_id": "deepseek/deepseek-v4-pro-0813", "name": "DeepSeek: DeepSeek V4 Pro 0813", "value": 0.7793333, "total_tasks": 500 }, { "rank": 11, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Anthropic: Claude Opus 4.8", "value": 0.7688890833333333, "total_tasks": 600 }, { "rank": 12, "permaslug": "google/gemini-3.5-flash-lite-20260721", "catalog_id": "google/gemini-3.5-flash-lite", "name": "Google: Gemini 3.5 Flash Lite", "value": 0.7688886666666668, "total_tasks": 150 }, { "rank": 13, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "Z.ai: GLM 5.3", "value": 0.768333375, "total_tasks": 400 }, { "rank": 14, "permaslug": "xiaomi/mimo-v2.6-pro-20260921", "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "Xiaomi: MiMo-V2.6-Pro", "value": 0.7679998, "total_tasks": 250 }, { "rank": 15, "permaslug": "z-ai/glm-5.3", "catalog_id": "z-ai/glm-5.3", "name": "GLM 5.3", "value": 0.76, "total_tasks": 50 }, { "rank": 16, "permaslug": "tencent/hy4-preview-20260827", "catalog_id": "tencent/hy4-preview", "name": "Tencent: Hy4 preview", "value": 0.7583335, "total_tasks": 200 }, { "rank": 17, "permaslug": "deepseek/deepseek-v4.1-flash-20260910", "catalog_id": "deepseek/deepseek-v4.1-flash", "name": "DeepSeek: DeepSeek V4.1 Flash", "value": 0.757778, "total_tasks": 300 }, { "rank": 18, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Anthropic: Claude Sonnet 5", "value": 0.7561111666666667, "total_tasks": 600 }, { "rank": 19, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "Z.ai: GLM 5.3 Flash", "value": 0.75583325, "total_tasks": 400 }, { "rank": 20, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "SpaceXAI: Grok 4.6", "value": 0.7533335, "total_tasks": 100 }, { "rank": 21, "permaslug": "qwen/qwen3.8-2.4t-a95b-20260812", "catalog_id": "qwen/qwen3.8-2.4t-a95b", "name": "Qwen: Qwen3.8 2.4T A95B", "value": 0.753333375, "total_tasks": 400 }, { "rank": 22, "permaslug": "qwen/qwen3.6-27b-20260422", "catalog_id": "qwen/qwen3.6-27b", "name": "Qwen: Qwen3.6 27B", "value": 0.75222225, "total_tasks": 600 }, { "rank": 23, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Anthropic: Claude Opus 5.5", "value": 0.752, "total_tasks": 250 }, { "rank": 24, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax: MiniMax M3", "value": 0.7488889166666667, "total_tasks": 600 }, { "rank": 25, "permaslug": "deepseek/deepseek-v4-flash-vision-exp-20260821", "catalog_id": "deepseek/deepseek-v4-flash-vision-exp", "name": "DeepSeek: DeepSeek V4 Flash Vision Exp", "value": 0.7480002, "total_tasks": 250 }, { "rank": 26, "permaslug": "meta/muse-spark-open-20261015", "catalog_id": "meta/muse-spark-open", "name": "Meta: Muse Spark Open", "value": 0.746667, "total_tasks": 50 }, { "rank": 27, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Google: Gemini 3.6 Flash", "value": 0.7466666666666667, "total_tasks": 150 }, { "rank": 28, "permaslug": "openai/gpt-5.6-sol-20260709", "catalog_id": "openai/gpt-5.6-sol", "name": "OpenAI: GPT-5.6 Sol", "value": 0.7466666666666667, "total_tasks": 150 }, { "rank": 29, "permaslug": "meta/muse-glimmer-30b-20260810", "catalog_id": "meta/muse-glimmer-30b", "name": "Meta: Muse Glimmer 30B", "value": 0.7466665714285714, "total_tasks": 350 }, { "rank": 30, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek: DeepSeek V4 Flash 0731", "value": 0.7430303636363637, "total_tasks": 550 }, { "rank": 31, "permaslug": "openai/gpt-5.6-sol-pro-20260709", "catalog_id": "openai/gpt-5.6-sol-pro", "name": "OpenAI: GPT-5.6 Sol Pro", "value": 0.736667, "total_tasks": 100 }, { "rank": 32, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "MoonshotAI: Kimi K2.7 Code", "value": 0.7355555, "total_tasks": 600 }, { "rank": 33, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek: DeepSeek V4.1 Flash 1017", "value": 0.7333330000000001, "total_tasks": 50 }, { "rank": 34, "permaslug": "nvidia/nemotron-3.5-super-vl-20261015", "catalog_id": "nvidia/nemotron-3.5-super-vl", "name": "NVIDIA: Nemotron 3.5 Super VL", "value": 0.7333330000000001, "total_tasks": 100 }, { "rank": 35, "permaslug": "openai/gpt-5.6-terra-20260709", "catalog_id": "openai/gpt-5.6-terra", "name": "OpenAI: GPT-5.6 Terra", "value": 0.7311113333333332, "total_tasks": 150 }, { "rank": 36, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Google: Gemini 3.5 Flash", "value": 0.7311110000000001, "total_tasks": 150 }, { "rank": 37, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "MoonshotAI: Kimi K3", "value": 0.7290908181818182, "total_tasks": 550 }, { "rank": 38, "permaslug": "openai/gpt-6-astra-pro-20260903", "catalog_id": "openai/gpt-6-astra-pro", "name": "OpenAI: GPT-6 Astra Pro", "value": 0.726667, "total_tasks": 50 }, { "rank": 39, "permaslug": "anthropic/claude-haiku-5.5-20261007", "catalog_id": "anthropic/claude-haiku-5.5", "name": "Anthropic: Claude Haiku 5.5", "value": 0.7266666666666667, "total_tasks": 150 }, { "rank": 40, "permaslug": "qwen/qwen3.6-35b-a3b-20260415", "catalog_id": "qwen/qwen3.6-35b-a3b", "name": "Qwen: Qwen3.6 35B A3B", "value": 0.7261505656565657, "total_tasks": 594 }, { "rank": 41, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "NVIDIA: Nemotron 3 Ultra", "value": 0.72, "total_tasks": 50 }, { "rank": 42, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen: Qwen3.7 Max", "value": 0.72, "total_tasks": 50 }, { "rank": 43, "permaslug": "google/gemini-3.1-flash-lite-20260507", "catalog_id": "google/gemini-3.1-flash-lite", "name": "Google: Gemini 3.1 Flash Lite", "value": 0.7199996666666667, "total_tasks": 150 }, { "rank": 44, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "Z.ai: GLM 5.2", "value": 0.7161110833333333, "total_tasks": 600 }, { "rank": 45, "permaslug": "qwen/qwen3.8-flash-20260826", "catalog_id": "qwen/qwen3.8-flash", "name": "Qwen: Qwen3.8 Flash", "value": 0.713333, "total_tasks": 50 }, { "rank": 46, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Google: Gemini 3.8 Flash", "value": 0.712766, "total_tasks": 47 }, { "rank": 47, "permaslug": "openai/gpt-5.6-luna-pro-20260709", "catalog_id": "openai/gpt-5.6-luna-pro", "name": "OpenAI: GPT-5.6 Luna Pro", "value": 0.7111113333333333, "total_tasks": 150 }, { "rank": 48, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen: Qwen3.7 Plus", "value": 0.703333, "total_tasks": 50 }, { "rank": 49, "permaslug": "openai/gpt-5.6-luna-20260709", "catalog_id": "openai/gpt-5.6-luna", "name": "OpenAI: GPT-5.6 Luna", "value": 0.7000003333333334, "total_tasks": 150 }, { "rank": 50, "permaslug": "z-ai/glm-5.3-flash", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM 5.3 Flash", "value": 0.7, "total_tasks": 50 }, { "rank": 51, "permaslug": "inclusionai/ling-3.0-flash-vl-20260910", "catalog_id": "inclusionai/ling-3.0-flash-vl", "name": "inclusionAI: Ling 3.0 Flash VL", "value": 0.7, "total_tasks": 50 }, { "rank": 52, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "OpenAI: GPT-6.1 Sol", "value": 0.7, "total_tasks": 50 }, { "rank": 53, "permaslug": "openai/gpt-6-sol-20260922", "catalog_id": "openai/gpt-6-sol", "name": "OpenAI: GPT-6 Sol", "value": 0.693333, "total_tasks": 50 }, { "rank": 54, "permaslug": "reflection/beam-1.0-501b-a23b-20261016", "catalog_id": "reflection/beam-1.0-501b-a23b", "name": "Reflection: Beam 1.0 501B A23B", "value": 0.693333, "total_tasks": 50 }, { "rank": 55, "permaslug": "inclusionai/ling-3.0-flash-20260723", "catalog_id": "inclusionai/ling-3.0-flash", "name": "inclusionAI: Ling 3.0 Flash", "value": 0.686667, "total_tasks": 50 }, { "rank": 56, "permaslug": "openai/gpt-6-astra-20260903", "catalog_id": "openai/gpt-6-astra", "name": "OpenAI: GPT-6 Astra", "value": 0.68, "total_tasks": 50 }, { "rank": 57, "permaslug": "openai/gpt-6-luna-20260922", "catalog_id": "openai/gpt-6-luna", "name": "OpenAI: GPT-6 Luna", "value": 0.673333, "total_tasks": 50 }, { "rank": 58, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Thinking Machines: Inkling", "value": 0.672, "total_tasks": 250 }, { "rank": 59, "permaslug": "openai/gpt-6-luna-pro-20260922", "catalog_id": "openai/gpt-6-luna-pro", "name": "OpenAI: GPT-6 Luna Pro", "value": 0.666667, "total_tasks": 50 }, { "rank": 60, "permaslug": "minimax/minimax-m3.1-flash-20261019", "catalog_id": "minimax/minimax-m3.1-flash", "name": "MiniMax: MiniMax M3.1 Flash", "value": 0.66, "total_tasks": 50 }, { "rank": 61, "permaslug": "nvidia/nemotron-3.5-lightning-20260807", "catalog_id": "nvidia/nemotron-3.5-lightning", "name": "NVIDIA: Nemotron 3.5 Lightning", "value": 0.6566381031518624, "total_tasks": 349 }, { "rank": 62, "permaslug": "thinkingmachines/inkling-small-20260730", "catalog_id": "thinkingmachines/inkling-small", "name": "Thinking Machines: Inkling Small", "value": 0.6066668000000001, "total_tasks": 250 }, { "rank": 63, "permaslug": "ibm-granite/granite-4.2-8b-20260831", "catalog_id": "ibm-granite/granite-4.2-8b", "name": "IBM: Granite 4.2 8B", "value": 0.583333, "total_tasks": 50 } ], "id": "or-tau_bench_verified_airline", "source": "openrouter", "group": "quality", "field": "accuracy", "direction": "higher_better", "missing_in_window": 74 }, { "ranked_count": 63, "scored_count": 63, "truncated": false, "rows": [ { "rank": 1, "permaslug": "inclusionai/ling-3.0-flash-20260723", "catalog_id": "inclusionai/ling-3.0-flash", "name": "inclusionAI: Ling 3.0 Flash", "value": 0.00219582, "total_tasks": 50 }, { "rank": 2, "permaslug": "inclusionai/ling-3.0-flash-vl-20260910", "catalog_id": "inclusionai/ling-3.0-flash-vl", "name": "inclusionAI: Ling 3.0 Flash VL", "value": 0.0030046400000000003, "total_tasks": 50 }, { "rank": 3, "permaslug": "z-ai/glm-5.3-flash", "catalog_id": "z-ai/glm-5.3-flash", "name": "GLM 5.3 Flash", "value": 0.00357748, "total_tasks": 50 }, { "rank": 4, "permaslug": "z-ai/glm-5.3-flash-20260826", "catalog_id": "z-ai/glm-5.3-flash", "name": "Z.ai: GLM 5.3 Flash", "value": 0.008674565, "total_tasks": 400 }, { "rank": 5, "permaslug": "deepseek/deepseek-v4-flash-20260731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek: DeepSeek V4 Flash 0731", "value": 0.009174501818181817, "total_tasks": 550 }, { "rank": 6, "permaslug": "openai/gpt-6-luna-20260922", "catalog_id": "openai/gpt-6-luna", "name": "OpenAI: GPT-6 Luna", "value": 0.00928508, "total_tasks": 50 }, { "rank": 7, "permaslug": "openai/gpt-5.6-luna-20260709", "catalog_id": "openai/gpt-5.6-luna", "name": "OpenAI: GPT-5.6 Luna", "value": 0.010915493333333333, "total_tasks": 150 }, { "rank": 8, "permaslug": "anthropic/claude-haiku-5.5-20261007", "catalog_id": "anthropic/claude-haiku-5.5", "name": "Anthropic: Claude Haiku 5.5", "value": 0.011438460000000001, "total_tasks": 150 }, { "rank": 9, "permaslug": "minimax/minimax-m3.1-flash-20261019", "catalog_id": "minimax/minimax-m3.1-flash", "name": "MiniMax: MiniMax M3.1 Flash", "value": 0.013329200000000001, "total_tasks": 50 }, { "rank": 10, "permaslug": "xiaomi/mimo-v2.6-flash-20260921", "catalog_id": "xiaomi/mimo-v2.6-flash", "name": "Xiaomi: MiMo-V2.6-Flash", "value": 0.014457230000000001, "total_tasks": 200 }, { "rank": 11, "permaslug": "deepseek/deepseek-v4.1-flash-20261017", "catalog_id": "deepseek/deepseek-v4.1-flash-1017", "name": "DeepSeek: DeepSeek V4.1 Flash 1017", "value": 0.01490002, "total_tasks": 50 }, { "rank": 12, "permaslug": "ibm-granite/granite-4.2-8b-20260831", "catalog_id": "ibm-granite/granite-4.2-8b", "name": "IBM: Granite 4.2 8B", "value": 0.015297799999999999, "total_tasks": 50 }, { "rank": 13, "permaslug": "z-ai/glm-5.3", "catalog_id": "z-ai/glm-5.3", "name": "GLM 5.3", "value": 0.01597332, "total_tasks": 50 }, { "rank": 14, "permaslug": "qwen/qwen3.8-flash-20260826", "catalog_id": "qwen/qwen3.8-flash", "name": "Qwen: Qwen3.8 Flash", "value": 0.01665106, "total_tasks": 50 }, { "rank": 15, "permaslug": "nvidia/nemotron-3.5-lightning-20260807", "catalog_id": "nvidia/nemotron-3.5-lightning", "name": "NVIDIA: Nemotron 3.5 Lightning", "value": 0.01698823782234957, "total_tasks": 349 }, { "rank": 16, "permaslug": "minimax/minimax-m3-20260531", "catalog_id": "minimax/minimax-m3", "name": "MiniMax: MiniMax M3", "value": 0.02489698, "total_tasks": 600 }, { "rank": 17, "permaslug": "reflection/beam-1.0-501b-a23b-20261016", "catalog_id": "reflection/beam-1.0-501b-a23b", "name": "Reflection: Beam 1.0 501B A23B", "value": 0.02754302, "total_tasks": 50 }, { "rank": 18, "permaslug": "deepseek/deepseek-v4-flash-vision-exp-20260821", "catalog_id": "deepseek/deepseek-v4-flash-vision-exp", "name": "DeepSeek: DeepSeek V4 Flash Vision Exp", "value": 0.030171100000000003, "total_tasks": 250 }, { "rank": 19, "permaslug": "inclusionai/ling-3.1-flash-20261002", "catalog_id": "inclusionai/ling-3.1-flash", "name": "inclusionAI: Ling 3.1 Flash", "value": 0.03146312, "total_tasks": 50 }, { "rank": 20, "permaslug": "deepseek/deepseek-v4.1-flash-20260910", "catalog_id": "deepseek/deepseek-v4.1-flash", "name": "DeepSeek: DeepSeek V4.1 Flash", "value": 0.03362461666666666, "total_tasks": 300 }, { "rank": 21, "permaslug": "meta/muse-glimmer-30b-20260810", "catalog_id": "meta/muse-glimmer-30b", "name": "Meta: Muse Glimmer 30B", "value": 0.03743281428571429, "total_tasks": 350 }, { "rank": 22, "permaslug": "openai/gpt-6-luna-pro-20260922", "catalog_id": "openai/gpt-6-luna-pro", "name": "OpenAI: GPT-6 Luna Pro", "value": 0.038762819999999996, "total_tasks": 50 }, { "rank": 23, "permaslug": "nvidia/nemotron-3.5-super-vl-20261015", "catalog_id": "nvidia/nemotron-3.5-super-vl", "name": "NVIDIA: Nemotron 3.5 Super VL", "value": 0.038872460000000005, "total_tasks": 100 }, { "rank": 24, "permaslug": "qwen/qwen3.6-35b-a3b-20260415", "catalog_id": "qwen/qwen3.6-35b-a3b", "name": "Qwen: Qwen3.6 35B A3B", "value": 0.04286990067340068, "total_tasks": 594 }, { "rank": 25, "permaslug": "z-ai/glm-5.2-20260616", "catalog_id": "z-ai/glm-5.2", "name": "Z.ai: GLM 5.2", "value": 0.04424442, "total_tasks": 600 }, { "rank": 26, "permaslug": "thinkingmachines/inkling-small-20260730", "catalog_id": "thinkingmachines/inkling-small", "name": "Thinking Machines: Inkling Small", "value": 0.046513716, "total_tasks": 250 }, { "rank": 27, "permaslug": "qwen/qwen3.7-plus-20260602", "catalog_id": "qwen/qwen3.7-plus", "name": "Qwen: Qwen3.7 Plus", "value": 0.05425128, "total_tasks": 50 }, { "rank": 28, "permaslug": "z-ai/glm-5.3-20260816", "catalog_id": "z-ai/glm-5.3", "name": "Z.ai: GLM 5.3", "value": 0.05900729999999999, "total_tasks": 400 }, { "rank": 29, "permaslug": "qwen/qwen3.8-27b-20260814", "catalog_id": "qwen/qwen3.8-27b", "name": "Qwen: Qwen3.8 27B", "value": 0.06914864222222221, "total_tasks": 450 }, { "rank": 30, "permaslug": "openai/gpt-5.6-luna-pro-20260709", "catalog_id": "openai/gpt-5.6-luna-pro", "name": "OpenAI: GPT-5.6 Luna Pro", "value": 0.07186812, "total_tasks": 150 }, { "rank": 31, "permaslug": "xiaomi/mimo-v2.6-pro-20260921", "catalog_id": "xiaomi/mimo-v2.6-pro", "name": "Xiaomi: MiMo-V2.6-Pro", "value": 0.07315105200000001, "total_tasks": 250 }, { "rank": 32, "permaslug": "moonshotai/kimi-k2.7-code-20260612", "catalog_id": "moonshotai/kimi-k2.7-code", "name": "MoonshotAI: Kimi K2.7 Code", "value": 0.07820470500000001, "total_tasks": 600 }, { "rank": 33, "permaslug": "thinkingmachines/inkling-20260715", "catalog_id": "thinkingmachines/inkling", "name": "Thinking Machines: Inkling", "value": 0.07962264, "total_tasks": 250 }, { "rank": 34, "permaslug": "meta/muse-spark-open-20261015", "catalog_id": "meta/muse-spark-open", "name": "Meta: Muse Spark Open", "value": 0.08652918, "total_tasks": 50 }, { "rank": 35, "permaslug": "google/gemini-3.1-flash-lite-20260507", "catalog_id": "google/gemini-3.1-flash-lite", "name": "Google: Gemini 3.1 Flash Lite", "value": 0.09322211333333333, "total_tasks": 150 }, { "rank": 36, "permaslug": "google/gemini-3.5-flash-lite-20260721", "catalog_id": "google/gemini-3.5-flash-lite", "name": "Google: Gemini 3.5 Flash Lite", "value": 0.09783254, "total_tasks": 150 }, { "rank": 37, "permaslug": "deepseek/deepseek-v4-pro-20260813", "catalog_id": "deepseek/deepseek-v4-pro-0813", "name": "DeepSeek: DeepSeek V4 Pro 0813", "value": 0.09867859, "total_tasks": 500 }, { "rank": 38, "permaslug": "openai/gpt-6.1-sol-20260929", "catalog_id": "openai/gpt-6.1-sol", "name": "OpenAI: GPT-6.1 Sol", "value": 0.1012818, "total_tasks": 50 }, { "rank": 39, "permaslug": "openai/gpt-5.6-terra-20260709", "catalog_id": "openai/gpt-5.6-terra", "name": "OpenAI: GPT-5.6 Terra", "value": 0.10536965333333334, "total_tasks": 150 }, { "rank": 40, "permaslug": "tencent/hy4-preview-20260827", "catalog_id": "tencent/hy4-preview", "name": "Tencent: Hy4 preview", "value": 0.12354291499999999, "total_tasks": 200 }, { "rank": 41, "permaslug": "openai/gpt-6-sol-20260922", "catalog_id": "openai/gpt-6-sol", "name": "OpenAI: GPT-6 Sol", "value": 0.12999802000000002, "total_tasks": 50 }, { "rank": 42, "permaslug": "qwen/qwen3.6-27b-20260422", "catalog_id": "qwen/qwen3.6-27b", "name": "Qwen: Qwen3.6 27B", "value": 0.13807676666666668, "total_tasks": 600 }, { "rank": 43, "permaslug": "google/gemini-3.7-flash-20260813", "catalog_id": "google/gemini-3.7-flash", "name": "Google: Gemini 3.7 Flash", "value": 0.14992966438356164, "total_tasks": 146 }, { "rank": 44, "permaslug": "nvidia/nemotron-3-ultra-550b-a55b-20260604", "catalog_id": "nvidia/nemotron-3-ultra-550b-a55b", "name": "NVIDIA: Nemotron 3 Ultra", "value": 0.15154258, "total_tasks": 50 }, { "rank": 45, "permaslug": "anthropic/claude-sonnet-5.5-20260928", "catalog_id": "anthropic/claude-sonnet-5.5", "name": "Anthropic: Claude Sonnet 5.5", "value": 0.15998305999999998, "total_tasks": 200 }, { "rank": 46, "permaslug": "openai/gpt-5.6-sol-20260709", "catalog_id": "openai/gpt-5.6-sol", "name": "OpenAI: GPT-5.6 Sol", "value": 0.18399340666666666, "total_tasks": 150 }, { "rank": 47, "permaslug": "qwen/qwen3.8-2.4t-a95b-20260812", "catalog_id": "qwen/qwen3.8-2.4t-a95b", "name": "Qwen: Qwen3.8 2.4T A95B", "value": 0.1921822125, "total_tasks": 400 }, { "rank": 48, "permaslug": "anthropic/claude-sonnet-5-20260630", "catalog_id": "anthropic/claude-sonnet-5", "name": "Anthropic: Claude Sonnet 5", "value": 0.20050754833333334, "total_tasks": 600 }, { "rank": 49, "permaslug": "google/gemini-3.8-flash-20260902", "catalog_id": "google/gemini-3.8-flash", "name": "Google: Gemini 3.8 Flash", "value": 0.21022357446808512, "total_tasks": 47 }, { "rank": 50, "permaslug": "google/gemini-3.6-flash-20260721", "catalog_id": "google/gemini-3.6-flash", "name": "Google: Gemini 3.6 Flash", "value": 0.21412848666666662, "total_tasks": 150 }, { "rank": 51, "permaslug": "moonshotai/kimi-k3-20260715", "catalog_id": "moonshotai/kimi-k3", "name": "MoonshotAI: Kimi K3", "value": 0.2888466727272727, "total_tasks": 550 }, { "rank": 52, "permaslug": "x-ai/grok-4.6-20260810", "catalog_id": "x-ai/grok-4.6", "name": "SpaceXAI: Grok 4.6", "value": 0.33087047999999997, "total_tasks": 100 }, { "rank": 53, "permaslug": "anthropic/claude-opus-5.5-20260921", "catalog_id": "anthropic/claude-opus-5.5", "name": "Anthropic: Claude Opus 5.5", "value": 0.33952648, "total_tasks": 250 }, { "rank": 54, "permaslug": "google/gemini-3.5-flash-20260519", "catalog_id": "google/gemini-3.5-flash", "name": "Google: Gemini 3.5 Flash", "value": 0.3988358066666667, "total_tasks": 150 }, { "rank": 55, "permaslug": "qwen/qwen3.7-max-20260520", "catalog_id": "qwen/qwen3.7-max", "name": "Qwen: Qwen3.7 Max", "value": 0.402901, "total_tasks": 50 }, { "rank": 56, "permaslug": "anthropic/claude-opus-5-20260723", "catalog_id": "anthropic/claude-opus-5", "name": "Anthropic: Claude Opus 5", "value": 0.48297491666666664, "total_tasks": 600 }, { "rank": 57, "permaslug": "anthropic/claude-4.8-opus-20260528", "catalog_id": "anthropic/claude-opus-4.8", "name": "Anthropic: Claude Opus 4.8", "value": 0.4929804266666666, "total_tasks": 600 }, { "rank": 58, "permaslug": "google/gemini-4-argon-20261013", "catalog_id": "google/gemini-4-argon", "name": "Google: Gemini 4 Argon", "value": 0.49828548, "total_tasks": 50 }, { "rank": 59, "permaslug": "openai/gpt-6-astra-20260903", "catalog_id": "openai/gpt-6-astra", "name": "OpenAI: GPT-6 Astra", "value": 0.58024224, "total_tasks": 50 }, { "rank": 60, "permaslug": "anthropic/claude-fable-5.1-20260831", "catalog_id": "anthropic/claude-fable-5.1", "name": "Anthropic: Claude Fable 5.1", "value": 0.71616581, "total_tasks": 200 }, { "rank": 61, "permaslug": "anthropic/claude-5-fable-20260609", "catalog_id": "anthropic/claude-fable-5", "name": "Anthropic: Claude Fable 5", "value": 0.9154123233333333, "total_tasks": 600 }, { "rank": 62, "permaslug": "openai/gpt-5.6-sol-pro-20260709", "catalog_id": "openai/gpt-5.6-sol-pro", "name": "OpenAI: GPT-5.6 Sol Pro", "value": 1.2879983000000002, "total_tasks": 100 }, { "rank": 63, "permaslug": "openai/gpt-6-astra-pro-20260903", "catalog_id": "openai/gpt-6-astra-pro", "name": "OpenAI: GPT-6 Astra Pro", "value": 2.91364046, "total_tasks": 50 } ], "id": "or-tau_bench_verified_airline-cost", "source": "openrouter", "group": "value", "field": "avg_cost_per_task", "direction": "lower_better", "missing_in_window": 74 }, { "ranked_count": 4, "scored_count": 4, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-opus-5", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 0.8924368823529413, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 595 }, { "rank": 2, "permaslug": "openai/gpt-5.6-sol", "catalog_id": "openai/gpt-5.6-sol", "name": "GPT-5.6-Sol", "value": 0.8243670000000001, "search_engine": "perplexity", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 632 }, { "rank": 3, "permaslug": "deepseek/deepseek-v4-flash-0731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "Deepseek V4 Flash 0731", "value": 0.77, "search_engine": "perplexity", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 100 }, { "rank": 4, "permaslug": "openai/gpt-5.6-luna", "catalog_id": "openai/gpt-5.6-luna", "name": "GPT-5.6-Luna", "value": 0.74, "search_engine": "perplexity", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "xhigh", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 100 } ], "id": "or-search_browsecomp", "source": "openrouter", "group": "quality", "field": "primary_score", "direction": "higher_better", "missing_in_window": 131 }, { "ranked_count": 4, "scored_count": 4, "truncated": false, "rows": [ { "rank": 1, "permaslug": "deepseek/deepseek-v4-flash-0731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "Deepseek V4 Flash 0731", "value": 0.07649624000000001, "search_engine": "perplexity", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 100 }, { "rank": 2, "permaslug": "openai/gpt-5.6-luna", "catalog_id": "openai/gpt-5.6-luna", "name": "GPT-5.6-Luna", "value": 0.09858238, "search_engine": "perplexity", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "xhigh", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 100 }, { "rank": 3, "permaslug": "openai/gpt-5.6-sol", "catalog_id": "openai/gpt-5.6-sol", "name": "GPT-5.6-Sol", "value": 0.5028527816455696, "search_engine": "perplexity", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 632 }, { "rank": 4, "permaslug": "anthropic/claude-opus-5", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 2.362899736134454, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 595 } ], "id": "or-search_browsecomp-cost", "source": "openrouter", "group": "value", "field": "avg_cost_per_task", "direction": "lower_better", "missing_in_window": 131 }, { "ranked_count": 4, "scored_count": 4, "truncated": false, "rows": [ { "rank": 1, "permaslug": "openai/gpt-5.6-luna", "catalog_id": "openai/gpt-5.6-luna", "name": "GPT-5.6-Luna", "value": 111189.6, "search_engine": "perplexity", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "xhigh", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 100 }, { "rank": 2, "permaslug": "openai/gpt-5.6-sol", "catalog_id": "openai/gpt-5.6-sol", "name": "GPT-5.6-Sol", "value": 115870.25, "search_engine": "perplexity", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 632 }, { "rank": 3, "permaslug": "deepseek/deepseek-v4-flash-0731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "Deepseek V4 Flash 0731", "value": 135422.98, "search_engine": "perplexity", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 100 }, { "rank": 4, "permaslug": "anthropic/claude-opus-5", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 140773.74453781513, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 595 } ], "id": "or-search_browsecomp-latency", "source": "openrouter", "group": "speed", "field": "avg_latency_per_task_ms", "direction": "lower_better", "missing_in_window": 131 }, { "ranked_count": 2, "scored_count": 2, "truncated": false, "rows": [ { "rank": 1, "permaslug": "openai/gpt-5.6-sol", "catalog_id": "openai/gpt-5.6-sol", "name": "GPT-5.6-Sol", "value": 0.71, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 100 }, { "rank": 2, "permaslug": "anthropic/claude-opus-5", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 0.67319, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 511 } ], "id": "or-search_hle", "source": "openrouter", "group": "quality", "field": "primary_score", "direction": "higher_better", "missing_in_window": 133 }, { "ranked_count": 2, "scored_count": 2, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-opus-5", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 0.40724371037182, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 511 }, { "rank": 2, "permaslug": "openai/gpt-5.6-sol", "catalog_id": "openai/gpt-5.6-sol", "name": "GPT-5.6-Sol", "value": 0.70518885, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 100 } ], "id": "or-search_hle-cost", "source": "openrouter", "group": "value", "field": "avg_cost_per_task", "direction": "lower_better", "missing_in_window": 133 }, { "ranked_count": 2, "scored_count": 2, "truncated": false, "rows": [ { "rank": 1, "permaslug": "openai/gpt-5.6-sol", "catalog_id": "openai/gpt-5.6-sol", "name": "GPT-5.6-Sol", "value": 85213.49, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 100 }, { "rank": 2, "permaslug": "anthropic/claude-opus-5", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 124923.79256360079, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 511 } ], "id": "or-search_hle-latency", "source": "openrouter", "group": "speed", "field": "avg_latency_per_task_ms", "direction": "lower_better", "missing_in_window": 133 }, { "ranked_count": 4, "scored_count": 4, "truncated": false, "rows": [ { "rank": 1, "permaslug": "anthropic/claude-opus-5", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 0.887391, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 300 }, { "rank": 2, "permaslug": "openai/gpt-5.6-sol", "catalog_id": "openai/gpt-5.6-sol", "name": "GPT-5.6-Sol", "value": 0.88378, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 450 }, { "rank": 3, "permaslug": "openai/gpt-5.6-luna", "catalog_id": "openai/gpt-5.6-luna", "name": "GPT-5.6-Luna", "value": 0.874766, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "xhigh", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 100 }, { "rank": 4, "permaslug": "deepseek/deepseek-v4-flash-0731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "Deepseek V4 Flash 0731", "value": 0.816547, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 100 } ], "id": "or-search_dsqa", "source": "openrouter", "group": "quality", "field": "primary_score", "direction": "higher_better", "missing_in_window": 131 }, { "ranked_count": 4, "scored_count": 4, "truncated": false, "rows": [ { "rank": 1, "permaslug": "deepseek/deepseek-v4-flash-0731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "Deepseek V4 Flash 0731", "value": 0.09063391, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 100 }, { "rank": 2, "permaslug": "openai/gpt-5.6-luna", "catalog_id": "openai/gpt-5.6-luna", "name": "GPT-5.6-Luna", "value": 0.10504530000000001, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "xhigh", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 100 }, { "rank": 3, "permaslug": "anthropic/claude-opus-5", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 0.7882165633333333, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 300 }, { "rank": 4, "permaslug": "openai/gpt-5.6-sol", "catalog_id": "openai/gpt-5.6-sol", "name": "GPT-5.6-Sol", "value": 0.8521226622222222, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 450 } ], "id": "or-search_dsqa-cost", "source": "openrouter", "group": "value", "field": "avg_cost_per_task", "direction": "lower_better", "missing_in_window": 131 }, { "ranked_count": 4, "scored_count": 4, "truncated": false, "rows": [ { "rank": 1, "permaslug": "deepseek/deepseek-v4-flash-0731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "Deepseek V4 Flash 0731", "value": 98765, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 100 }, { "rank": 2, "permaslug": "openai/gpt-5.6-luna", "catalog_id": "openai/gpt-5.6-luna", "name": "GPT-5.6-Luna", "value": 100178.74, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "xhigh", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 100 }, { "rank": 3, "permaslug": "openai/gpt-5.6-sol", "catalog_id": "openai/gpt-5.6-sol", "name": "GPT-5.6-Sol", "value": 130880.1888888889, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 450 }, { "rank": 4, "permaslug": "anthropic/claude-opus-5", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 143767.81333333332, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "accuracy", "total_tasks": 300 } ], "id": "or-search_dsqa-latency", "source": "openrouter", "group": "speed", "field": "avg_latency_per_task_ms", "direction": "lower_better", "missing_in_window": 131 }, { "ranked_count": 4, "scored_count": 4, "truncated": false, "rows": [ { "rank": 1, "permaslug": "openai/gpt-5.6-sol", "catalog_id": "openai/gpt-5.6-sol", "name": "GPT-5.6-Sol", "value": 0.84049, "search_engine": "perplexity", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "f1_by_item", "total_tasks": 100 }, { "rank": 2, "permaslug": "openai/gpt-5.6-luna", "catalog_id": "openai/gpt-5.6-luna", "name": "GPT-5.6-Luna", "value": 0.834223, "search_engine": "perplexity", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "xhigh", "temperature": null }, "primary_metric": "f1_by_item", "total_tasks": 100 }, { "rank": 3, "permaslug": "deepseek/deepseek-v4-flash-0731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "Deepseek V4 Flash 0731", "value": 0.771289, "search_engine": "perplexity", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "f1_by_item", "total_tasks": 100 }, { "rank": 4, "permaslug": "anthropic/claude-opus-5", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 0.6725280000000001, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "f1_by_item", "total_tasks": 100 } ], "id": "or-search_widesearch", "source": "openrouter", "group": "quality", "field": "primary_score", "direction": "higher_better", "missing_in_window": 131 }, { "ranked_count": 4, "scored_count": 4, "truncated": false, "rows": [ { "rank": 1, "permaslug": "deepseek/deepseek-v4-flash-0731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "Deepseek V4 Flash 0731", "value": 0.10469292, "search_engine": "perplexity", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "f1_by_item", "total_tasks": 100 }, { "rank": 2, "permaslug": "openai/gpt-5.6-luna", "catalog_id": "openai/gpt-5.6-luna", "name": "GPT-5.6-Luna", "value": 0.16628389, "search_engine": "perplexity", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "xhigh", "temperature": null }, "primary_metric": "f1_by_item", "total_tasks": 100 }, { "rank": 3, "permaslug": "openai/gpt-5.6-sol", "catalog_id": "openai/gpt-5.6-sol", "name": "GPT-5.6-Sol", "value": 0.83365428, "search_engine": "perplexity", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "f1_by_item", "total_tasks": 100 }, { "rank": 4, "permaslug": "anthropic/claude-opus-5", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 1.36199698, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "f1_by_item", "total_tasks": 100 } ], "id": "or-search_widesearch-cost", "source": "openrouter", "group": "value", "field": "avg_cost_per_task", "direction": "lower_better", "missing_in_window": 131 }, { "ranked_count": 4, "scored_count": 4, "truncated": false, "rows": [ { "rank": 1, "permaslug": "deepseek/deepseek-v4-flash-0731", "catalog_id": "deepseek/deepseek-v4-flash-0731", "name": "Deepseek V4 Flash 0731", "value": 118587.16, "search_engine": "perplexity", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "f1_by_item", "total_tasks": 100 }, { "rank": 2, "permaslug": "openai/gpt-5.6-sol", "catalog_id": "openai/gpt-5.6-sol", "name": "GPT-5.6-Sol", "value": 135725.25, "search_engine": "perplexity", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "f1_by_item", "total_tasks": 100 }, { "rank": 3, "permaslug": "openai/gpt-5.6-luna", "catalog_id": "openai/gpt-5.6-luna", "name": "GPT-5.6-Luna", "value": 164892, "search_engine": "perplexity", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "xhigh", "temperature": null }, "primary_metric": "f1_by_item", "total_tasks": 100 }, { "rank": 4, "permaslug": "anthropic/claude-opus-5", "catalog_id": "anthropic/claude-opus-5", "name": "Claude Opus 5", "value": 217914.03, "search_engine": "parallel", "search_surface": "server-tool", "run_config": { "max_agent_turns": 25, "reasoning_effort": "high", "temperature": null }, "primary_metric": "f1_by_item", "total_tasks": 100 } ], "id": "or-search_widesearch-latency", "source": "openrouter", "group": "speed", "field": "avg_latency_per_task_ms", "direction": "lower_better", "missing_in_window": 131 } ] }