Sign in
Computed automatically· 18 categories · 1244 public models · verified Oct 15, 2026

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.

IsSOTA?
Current crowns · Oct 15, 2026

Who is SOTA right now

General LLM
G
Gemini 4 Argon
Gemini 4 Argon holds the confirmed General LLM crown since 2026-10-02.…13d reign
ReasoningCO-SOTA
AG
Claude Opus 5.5 & Gemini 4 Argon
Claude Opus 5.5 holds the confirmed Reasoning crown since 2026-10-02.…13d reign
Math
O
GPT-6 Astra
GPT-6 Astra is SOTA in Math since 2026-09-28. No eligible model is…17d reign
CodingCO-SOTA
AA
Claude Opus 5.5 & Claude Sonnet 5.5
Claude Opus 5.5 is tied for SOTA in Coding with Claude Sonnet 5.5,…9d reign
Coding › AgenticCO-SOTA
AA
Claude Opus 5.5 & Claude Sonnet 5.5
Claude Opus 5.5 is tied for SOTA in Coding › Agentic with Claude…9d reign
Coding › Web dev
A
Claude Opus 5.5
Claude Opus 5.5 is SOTA in Coding › Web dev since 2026-09-29. No…16d reign
Long contextCO-SOTA
AG
Claude Opus 5.5 & Gemini 4 Argon
Claude Opus 5.5 is tied for SOTA in Long context with Gemini 4 Argon,…13d reign
VisionCO-SOTA
AOO
Claude Sonnet 5.5 & GPT-6.1 Sol & GPT-6 Astra
Claude Sonnet 5.5 is tied for SOTA in Vision with GPT-6 Astra, GPT-6.1…15d reign
Image generation
O
GPT Image 2.5 Sunburst
GPT Image 2.5 Sunburst is SOTA in Image generation since 2026-09-24.…21d reign
Image edit
O
GPT Image 2.5 Sunburst
GPT Image 2.5 Sunburst is SOTA in Image edit since 2026-09-22. No…23d reign
Video generation
O
Sora 2
Sora 2 holds the confirmed Video generation crown since 2025-10-17.…363d reign
FactualityCO-SOTA
AAG
Claude Fable 5.1 & Claude Opus 5.5 & Gemini 4 Argon
Claude Fable 5.1 holds the confirmed Factuality crown since…13d reign
EmbeddingsCO-SOTA
MSQTE
Microsoft Harrier Oss V1 27B & Qwen Qwen3 Embedding 8B & Tencent Kalm Embedding Gemma3 12B 2511
Microsoft Harrier Oss V1 27B is tied for SOTA in Embeddings with Qwen…197d reign
Decision modelsCO-SOTA
MIPEVL
linne-oak 1.0 (31B) & Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) & vLLM-SR d3 (27B)
linne-oak 1.0 (31B) is co-SOTA in Decision models with low confidence…1d reign

Every crown is computed automatically from independent primary evidence. How we decide → This month's recap

Since Oct 15, 2026 minus 7 days

New this week

Latest rulings

Crown changes

Full changelog →
Awaiting evidence

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.

Use the answer anywhere

Free API, MCP, badges & RSS