Is it state of the art?
Type any AI model. Get a straight, dated answer per category: yes, close, it used to be, or its best rank. With receipts.
Who is SOTA right now
Every crown is computed automatically from independent primary evidence. How we decide → This month's recap October 2026 recap
New this week
- Nov 6, 2026 — First benchmark: REAX 1.3 on Decision Index Full
- Nov 6, 2026 — First benchmark: Gemini Omni 1.2 Flash on LMArena Text-to-Video
- Nov 6, 2026 — Video generation (best per dollar): Gemini Omni 1.2 Flash takes the crown
- Nov 6, 2026 — Reasoning (best per dollar): DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 3.7 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 and GLM 5.3 Flash and Hy3 are co-SOTA
- Nov 6, 2026 — Reasoning (best per dollar): DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 3.7 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 and GLM 5.3 Flash are co-SOTA
- Nov 6, 2026 — Long context (best per dollar): DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 3.7 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 and GLM 5.3 Flash and Mimo V2.6 Pro are co-SOTA
- Nov 6, 2026 — Long context (best per dollar): DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 3.7 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 and GLM 5.3 Flash and Hy3 and Mimo V2.6 Pro are co-SOTA
- Nov 6, 2026 — General LLM (best per dollar): DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 3.7 Flash and Gemini 4 Argon and Muse Spark 1.2 and Muse Spark 1.3 are co-SOTA
- Nov 6, 2026 — General LLM (best per dollar): DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 3.7 Flash and Gemini 4 Argon and Hy3 and Muse Spark 1.2 and Muse Spark 1.3 are co-SOTA
- Nov 6, 2026 — Factuality (best per dollar): Claude Opus 5.5 and DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 4 Argon and GPT Oss 120B and Mimo V2.6 Pro are co-SOTA
- Nov 6, 2026 — Factuality (best per dollar): Claude Opus 5.5 and DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 4 Argon and GPT Oss 120B and Hy3 and Mimo V2.6 Pro are co-SOTA
- Nov 6, 2026 — Cybersecurity (best per dollar): Claude Haiku 5.5 and Gemini 3.8 Flash and GLM 5.3 and GPT-6.1 Sol and GPT-6 Astra and Mimo V2.6 Flash are co-SOTA
- Nov 6, 2026 — Coding › Web dev (best per dollar): Claude Opus 5.5 and Claude Sonnet 5.5 and DeepSeek V4.1 Flash and DeepSeek V4 Flash and GPT-6.1 Sol and MiniMax M3.1 Flash are co-SOTA
- Nov 6, 2026 — Coding › Web dev (best per dollar): Claude Opus 5.5 and Claude Sonnet 5.5 and DeepSeek V4.1 Flash and DeepSeek V4 Flash and GPT-6.1 Sol are co-SOTA
- Nov 6, 2026 — Coding (best per dollar): Claude Opus 5.5 and Claude Sonnet 5.5 and DeepSeek V4.1 Flash and DeepSeek V4.1 Flash 1017 and Mercury 3 are co-SOTA
- Nov 6, 2026 — Decision models: REAX 1.3 and GLiDE 27B and Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) are co-SOTA
- Nov 6, 2026 — Decision models: REAX 1.3 and GLiDE 27B and Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) are co-SOTA
- Nov 6, 2026 — Decision models: GLiDE 27B and Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) are co-SOTA
- Nov 5, 2026 — First benchmark: Hy4 on Vals Index
- Nov 5, 2026 — First benchmark: GPT-Image-2.6 Sunburst on LMArena Text-to-Image
- Nov 5, 2026 — First benchmark: GPT-Image-2.6 Flare on LMArena Text-to-Image
- Nov 5, 2026 — Reasoning (best per dollar): DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 3.7 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 and GLM 5.3 Flash and Hy3 are co-SOTA
- Nov 5, 2026 — Reasoning (best per dollar): DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 3.7 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 and GLM 5.3 Flash are co-SOTA
- Nov 5, 2026 — Long context (best per dollar): DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 3.7 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 and GLM 5.3 Flash and Mimo V2.6 Pro are co-SOTA
- Nov 5, 2026 — Long context (best per dollar): DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 3.7 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 and GLM 5.3 Flash and Hy3 and Mimo V2.6 Pro are co-SOTA
- Nov 5, 2026 — General LLM (best per dollar): DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 3.7 Flash and Gemini 4 Argon and Muse Spark 1.2 and Muse Spark 1.3 are co-SOTA
- Nov 5, 2026 — General LLM (best per dollar): DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 3.7 Flash and Gemini 4 Argon and Hy3 and Muse Spark 1.2 and Muse Spark 1.3 are co-SOTA
- Nov 5, 2026 — Factuality (best per dollar): Claude Opus 5.5 and DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 4 Argon and Granite 4.2 8B and Mimo V2.6 Pro are co-SOTA
- Nov 5, 2026 — Factuality (best per dollar): Claude Opus 5.5 and DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 4 Argon and GPT Oss 120B and Mimo V2.6 Pro are co-SOTA
- Nov 5, 2026 — Factuality (best per dollar): Claude Opus 5.5 and DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 4 Argon and GPT Oss 120B and Hy3 and Mimo V2.6 Pro are co-SOTA
- Nov 5, 2026 — Coding › Web dev (best per dollar): Claude Opus 5.5 and Claude Sonnet 5.5 and DeepSeek V4.1 Flash and DeepSeek V4 Flash and GPT-6.1 Sol and MiniMax M3.1 Flash are co-SOTA
- Nov 5, 2026 — Coding › Web dev (best per dollar): Claude Opus 5.5 and Claude Sonnet 5.5 and DeepSeek V4.1 Flash and DeepSeek V4 Flash and GPT-6.1 Sol are co-SOTA
- Nov 4, 2026 — First benchmark: LiquidAI d1-Omni-2B on Decision Index Full
- Nov 4, 2026 — First benchmark: LiquidAI d1-2B on Decision Index Full
- Nov 4, 2026 — Vision (best per dollar): DeepSeek V4.1 Flash and Gemini 3.7 Flash and GPT-6.1 Sol and GPT-6 Luna and Muse Spark 1.3 are co-SOTA
- Nov 4, 2026 — Reasoning (best per dollar): Gemini 3.7 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 and GLM 5.3 Flash are co-SOTA
- Nov 4, 2026 — Reasoning (best per dollar): DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 3.7 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 and GLM 5.3 Flash and Hy3 are co-SOTA
- Nov 4, 2026 — Long context (best per dollar): Gemini 3.7 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 and GLM 5.3 Flash and Mimo V2.6 Pro are co-SOTA
- Nov 4, 2026 — Long context (best per dollar): DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 3.7 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 and GLM 5.3 Flash and Hy3 and Mimo V2.6 Pro are co-SOTA
- Nov 4, 2026 — General LLM (best per dollar): DeepSeek V4.1 Flash and Gemini 3.7 Flash and Gemini 4 Argon and GLM 5.3 Flash and Muse Spark 1.2 and Muse Spark 1.3 are co-SOTA
- Nov 4, 2026 — General LLM (best per dollar): DeepSeek V4.1 Flash and Gemini 3.7 Flash and Gemini 4 Argon and GLM 5.3 Flash and Hy3 and Muse Spark 1.2 and Muse Spark 1.3 are co-SOTA
- Nov 4, 2026 — General LLM (best per dollar): DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 3.7 Flash and Gemini 4 Argon and Hy3 and Muse Spark 1.2 and Muse Spark 1.3 are co-SOTA
- Nov 4, 2026 — Finance (best per dollar): DeepSeek V4 Flash 0731 and GLM 5.3 Flash and GPT-5.6 Luna and Muse Spark 1.1 and Muse Spark 1.2 are co-SOTA
- Nov 4, 2026 — Cybersecurity (best per dollar): Claude Haiku 5.5 and DeepSeek V4.1 Flash and Gemini 3.8 Flash and GLM 5.3 and GPT-6.1 Sol and GPT-6 Astra and Mimo V2.6 Flash are co-SOTA
- Nov 4, 2026 — Coding › Web dev (best per dollar): Claude Opus 5.5 and Claude Sonnet 5.5 and DeepSeek V4.1 Flash and DeepSeek V4 Flash and GPT-6.1 Sol and MiniMax M3.1 Flash are co-SOTA
- Nov 4, 2026 — Coding › Agentic (best per dollar): Claude Opus 5.5 and Claude Sonnet 5.5 and GLM 5.3 and GLM 5.3 Flash and GPT-6 Luna are co-SOTA
- Nov 4, 2026 — Coding (best per dollar): Claude Opus 5.5 and Claude Sonnet 5.5 and DeepSeek V4.1 Flash and DeepSeek V4.1 Flash 1017 are co-SOTA
- Nov 4, 2026 — Image generation: Ideogram 4.0 takes the crown
- Nov 3, 2026 — General LLM (best per dollar): DeepSeek V4.1 Flash and Gemini 3.7 Flash and Gemini 4 Argon and GLM 5.3 Flash and Muse Spark 1.2 and Muse Spark 1.3 are co-SOTA
- Nov 3, 2026 — General LLM (best per dollar): DeepSeek V4.1 Flash and Gemini 3.7 Flash and Gemini 4 Argon and GLM 5.3 Flash and Hy3 and Muse Spark 1.2 and Muse Spark 1.3 are co-SOTA
- Nov 2, 2026 — General LLM (best per dollar): DeepSeek V4.1 Flash and Gemini 3.7 Flash and Gemini 4 Argon and GLM 5.3 Flash and Muse Spark 1.2 and Muse Spark 1.3 are co-SOTA
- Nov 2, 2026 — General LLM (best per dollar): DeepSeek V4.1 Flash and Gemini 3.7 Flash and Gemini 4 Argon and GLM 5.3 Flash and Hy3 and Muse Spark 1.2 and Muse Spark 1.3 are co-SOTA
- Nov 2, 2026 — Factuality (best per dollar): Claude Opus 5.5 and DeepSeek V4.1 Flash and Gemini 4 Argon and GLM 5.3 Flash and Mimo V2.6 Pro are co-SOTA
- Nov 1, 2026 — Reasoning (best per dollar): Gemini 3.7 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 Flash and Mimo V2.6 Pro are co-SOTA
- Nov 1, 2026 — Long context (best per dollar): Gemini 3.7 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 Flash and Mimo V2.6 Pro are co-SOTA
- Nov 1, 2026 — General LLM (best per dollar): DeepSeek V4.1 Flash and Gemini 3.7 Flash and Gemini 4 Argon and GLM 5.3 Flash and Muse Spark 1.2 and Muse Spark 1.3 are co-SOTA
- Nov 1, 2026 — General LLM (best per dollar): DeepSeek V4.1 Flash and Gemini 3.7 Flash and Gemini 4 Argon and GLM 5.3 Flash and Hy3 and Muse Spark 1.2 and Muse Spark 1.3 are co-SOTA
- Nov 1, 2026 — Factuality (best per dollar): Claude Opus 5.5 and DeepSeek V4.1 Flash and Gemini 4 Argon and GLM 5.3 Flash and GPT Oss 120B and Mimo V2.6 Pro are co-SOTA
- Oct 31, 2026 — Reasoning (best per dollar): Gemini 3.7 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 and GLM 5.3 Flash are co-SOTA
- Oct 31, 2026 — Long context (best per dollar): Gemini 3.7 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 and GLM 5.3 Flash and Mimo V2.6 Pro are co-SOTA
- Oct 31, 2026 — General LLM (best per dollar): DeepSeek V4.1 Flash and Gemini 3.7 Flash and Gemini 4 Argon and GLM 5.3 Flash and Hy3 and Muse Spark 1.2 and Muse Spark 1.3 are co-SOTA
- Oct 30, 2026 — Vision (best per dollar): DeepSeek V4.1 Flash and Gemini 3.7 Flash and GPT-6.1 Sol and GPT-6 Luna and Muse Spark 1.3 are co-SOTA
- Oct 30, 2026 — Vision (best per dollar): DeepSeek V4.1 Flash and Gemini 3.7 Flash and GLM 5.3 Flash and GPT-6.1 Sol and GPT-6 Luna and Muse Spark 1.3 are co-SOTA
- Oct 30, 2026 — Reasoning (best per dollar): Gemini 3.7 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 Flash and Mimo V2.6 Pro are co-SOTA
- Oct 30, 2026 — Reasoning (best per dollar): DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 3.7 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 Flash and Mimo V2.6 Pro are co-SOTA
- Oct 30, 2026 — Long context (best per dollar): Gemini 3.7 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 Flash and Mimo V2.6 Pro are co-SOTA
- Oct 30, 2026 — Long context (best per dollar): DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 3.7 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 Flash and Mimo V2.6 Pro are co-SOTA
- Oct 30, 2026 — General LLM (best per dollar): DeepSeek V4.1 Flash and Gemini 3.7 Flash and Gemini 4 Argon and GLM 5.3 Flash and Muse Spark 1.2 and Muse Spark 1.3 are co-SOTA
- Oct 30, 2026 — General LLM (best per dollar): DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 3.7 Flash and Gemini 4 Argon and Muse Spark 1.2 and Muse Spark 1.3 are co-SOTA
- Oct 30, 2026 — Finance (best per dollar): GLM 5.3 Flash and GPT-5.6 Luna and Muse Spark 1.1 and Muse Spark 1.2 are co-SOTA
- Oct 30, 2026 — Finance (best per dollar): DeepSeek V4 Flash 0731 and GLM 5.3 Flash and GPT-5.6 Luna and GPT-5 Nano and Muse Spark 1.1 and Muse Spark 1.2 are co-SOTA
- Oct 30, 2026 — Factuality (best per dollar): Claude Opus 5.5 and DeepSeek V4.1 Flash and Gemini 4 Argon and GLM 5.3 Flash and Mimo V2.6 Pro are co-SOTA
- Oct 30, 2026 — Factuality (best per dollar): Claude Opus 5.5 and DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 4 Argon and Granite 4.2 8B and Mimo V2.6 Pro are co-SOTA
- Oct 30, 2026 — Cybersecurity (best per dollar): Claude Haiku 5.5 and Gemini 3.8 Flash and GLM 5.3 and GLM 5.3 Flash and GPT-6.1 Sol and GPT-6 Astra and Mimo V2.6 Flash are co-SOTA
- Oct 30, 2026 — Cybersecurity (best per dollar): Claude Haiku 5.5 and DeepSeek V4.1 Flash and Gemini 3.8 Flash and GLM 5.3 and GPT-6.1 Sol and GPT-6 Astra and Mimo V2.6 Flash are co-SOTA
- Oct 30, 2026 — Coding › Web dev (best per dollar): Claude Opus 5.5 and Claude Sonnet 5.5 and DeepSeek V4.1 Flash and GLM 5.3 Flash and GPT-6.1 Sol are co-SOTA
- Oct 30, 2026 — Coding › Web dev (best per dollar): Claude Opus 5.5 and Claude Sonnet 5.5 and DeepSeek V4.1 Flash and DeepSeek V4 Flash and GPT-6.1 Sol are co-SOTA
- Oct 30, 2026 — Coding › Agentic (best per dollar): Claude Opus 5.5 and Claude Sonnet 5.5 and GLM 5.3 and GLM 5.3 Flash and GPT-6 Luna are co-SOTA
- Oct 30, 2026 — Coding › Agentic (best per dollar): Claude Opus 5.5 and Claude Sonnet 5.5 and GLM 5.3 and GLM 5.3 Flash are co-SOTA
- Oct 30, 2026 — Coding (best per dollar): Claude Opus 5.5 and Claude Sonnet 5.5 and DeepSeek V4.1 Flash and DeepSeek V4.1 Flash 1017 and GLM 5.3 Flash are co-SOTA
- Oct 30, 2026 — Coding (best per dollar): Claude Opus 5.5 and Claude Sonnet 5.5 and DeepSeek V4.1 Flash and DeepSeek V4.1 Flash 1017 are co-SOTA
Newly tracked
Also recently announced (pending benchmarks): Quark · Accentus · ERNIE-5.5-Flash-Base · GLiDE · GPT-6 Cyber · Higgs Realtime Duplex
Crown changes
Too new to call
A model under 7 days old stays pending only when it is close to the crown. Everyone else is ranked as soon as the board lists them. Vendor claims alone cannot take a crown.
Families, labs, recaps and best-of pages
Recaps: current and previous month
Labs with crowns
- Anthropic · 8 crowns
- OpenAI · 5 crowns
- Google DeepMind · 4 crowns
- Meta · 3 crowns
- Alibaba / Qwen · 1 crown
- Microsoft · 1 crown
- Tencent · 1 crown
Best models by task
Free API, MCP, badges & RSS
REST API
One call, one dated answer. Anonymous reads are free. A free API key raises the limit. Crown changes are on the RSS feed.
MCP server
Let an agent ask which model is best for a task.
Live badges
They become WAS SOTA when the crown moves. A ranked model shows its place.
Follow changes
A feed for the whole site, and one for every category.