⌕Is ___ SOTA?
Computed automatically· 17 categories · 98 models in this snapshot · verified Oct 13, 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 no. With receipts.

IsSOTA?
Current crowns · Oct 13, 2026

Who is SOTA right now

General LLM
G
Gemini 2.5 Pro
Gemini 2.5 Pro is SOTA in General LLM since 2026-01-27. No eligible…259d reign
ReasoningCO-SOTA
AGO
Claude Opus 5.5 & Gemini 4 Argon & GPT-6 Astra
Claude Opus 5.5 is co-SOTA in Reasoning with low confidence because…5d reign
MathCO-SOTA
GOM
Gemini 3.1 Pro Preview & GPT-5.4 Pro & Muse Spark
Gemini 3.1 Pro Preview is tied for SOTA in Math with GPT-5.4 Pro, Muse…180d 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,…7d 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…7d reign
Coding › Web dev
O
GPT-5.5
GPT-5.5 is SOTA in Coding › Web dev since 2026-05-25. No eligible…141d reign
Long contextCO-SOTA
OxO
GPT-5 & Grok 4 0709 & O3
GPT-5 is tied for SOTA in Long context with O3, Grok 4 0709, within…418d reign
VisionCO-SOTA
OO
GPT-5.6 Sol & GPT-6 Astra
GPT-5.6 Sol is tied for SOTA in Vision with GPT-6 Astra, within the…34d reign
Image generation
MS
Mai Image 2.5
Mai Image 2.5 is SOTA in Image generation since 2026-09-24. No…19d reign
Image edit
O
GPT Image 2.5 Sunburst
GPT Image 2.5 Sunburst is SOTA in Image edit since 2026-10-06. No…7d reign
Video generation
G
Veo 3
Veo 3 is SOTA in Video generation since 2026-03-06. No eligible model…221d reign
Factuality
M
Muse Spark 1.1
Muse Spark 1.1 is SOTA in Factuality since 2026-07-20. No eligible…85d 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…195d reign

Every crown is computed automatically from independent primary evidence. How we decide →

Latest rulings

Crown changes

Full changelog →
Awaiting evidence

Too early to call

A brand-new release stays pending until independent results arrive. Vendor claims alone cannot take a crown.

Use the answer anywhere

Free API, MCP, badges & alerts