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.
Current crowns · Oct 15, 2026
Who is SOTA right now
General LLM
G
Gemini 4 Argon
ReasoningCO-SOTA
AG
Claude Opus 5.5 & Gemini 4 Argon
Math
O
GPT-6 Astra
CodingCO-SOTA
AA
Claude Opus 5.5 & Claude Sonnet 5.5
Coding › AgenticCO-SOTA
AA
Claude Opus 5.5 & Claude Sonnet 5.5
Coding › Web dev
A
Claude Opus 5.5
Long contextCO-SOTA
AG
Claude Opus 5.5 & Gemini 4 Argon
VisionCO-SOTA
AOO
Claude Sonnet 5.5 & GPT-6.1 Sol & GPT-6 Astra
Image generation
O
GPT Image 2.5 Sunburst
Image edit
O
GPT Image 2.5 Sunburst
Video generation
O
Sora 2
FactualityCO-SOTA
AAG
Claude Fable 5.1 & Claude Opus 5.5 & Gemini 4 Argon
EmbeddingsCO-SOTA
MSQTE
Microsoft Harrier Oss V1 27B & Qwen Qwen3 Embedding 8B & Tencent Kalm Embedding Gemma3 12B 2511
Decision modelsCO-SOTA
MIPEVL
linne-oak 1.0 (31B) & Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) & vLLM-SR d3 (27B)
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
- Oct 14, 2026 — Decision models: board re-based
- Oct 14, 2026 — Decision models: vLLM-SR d3 (27B) and linne-oak 1.0 (31B) and Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) are co-SOTA
- Oct 14, 2026 — Decision models: board re-based
- Oct 14, 2026 — Decision models: vLLM-SR d3 (27B) and linne-oak 1.0 (31B) and Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) are co-SOTA
- Oct 14, 2026 — Decision models: board re-based
- Oct 14, 2026 — Decision models: vLLM-SR d3 (27B) and linne-oak 1.0 (31B) and Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) are co-SOTA
- Oct 14, 2026 — Decision models: Bobcat 1.3 (31B) takes the crown
- Oct 14, 2026 — Decision models › Vision: RSI-Jev v6.1 VL 27B (effort auto) takes the crown
- Oct 14, 2026 — Decision models: Nace.AI Drex v2.0 (35B-A3B) takes the crown
- Oct 13, 2026 — Reasoning: Kimi K3 and Mimo V2.6 Pro are co-SOTA
- Oct 13, 2026 — Long context: Kimi K3 and Mimo V2.6 Pro are co-SOTA
- Oct 13, 2026 — General LLM: Kimi K3 and Mimo V2.6 Pro and GLM 5.3 are co-SOTA
- Oct 8, 2026 — Decision models: decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) takes the crown
- Oct 8, 2026 — Decision models: Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) takes the crown
- Oct 8, 2026 — Decision models: Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) takes the crown
- Oct 8, 2026 — Reasoning: Gemma 4 31B and Qwen3 8 27B and Gemma 4 26B A4b are co-SOTA
- Oct 8, 2026 — Long context: Gemma 4 31B and Gemma 4 26B A4b are co-SOTA
- Oct 8, 2026 — General LLM: Gemma 4 31B and Gemma 4 26B A4b are co-SOTA
- Oct 8, 2026 — Factuality: Gemma 4 31B and Gemma 4 26B A4b and Qwen3 8 27B are co-SOTA
- Oct 8, 2026 — Decision models: Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) takes the crown
- Oct 8, 2026 — Decision models: Sage 1.3.0 (Levanto Labs) takes the crown
Latest rulings
Crown changes
Decision models: board re-basedDecision models: vLLM-SR d3 (27B) and linne-oak 1.0 (31B) and Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) are co-SOTADecision models: board re-basedDecision models: vLLM-SR d3 (27B) and linne-oak 1.0 (31B) and Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) are co-SOTADecision models: board re-basedDecision models: vLLM-SR d3 (27B) and linne-oak 1.0 (31B) and Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) are co-SOTA
Awaiting evidence
Too new to call
MMuse Wonder
MetaPending
MetaPending
MMuse Wonder
MetaPending
MetaPending
MMuse Wonder
MetaPending
MetaPending
MMuse Wonder
MetaPending
MetaPending
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
GET /v1/is-sota
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.isitsota.com
MCP server
Let an agent ask which model is best for a task.
?isitsotaSOTA · live
Live badges
They become WAS SOTA when the crown moves. A ranked model shows its place.
/rss.xml
Follow changes
A feed for the whole site, and one for every category.