⌕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?
Try: DeepSeek R1Gemini 4 ArgonGemma 3 27B ITLlama 3.3 70B Instruct best open model for coding
Current crowns · Oct 13, 2026

Who is SOTA right now

Slice:
OverallOpen weights≤ 32BBest per $
General LLM
DSGG
DeepSeek R1 & Gemini 4 Argon & Gemma 3 27B IT & Llama 3.3 70B Instruct & O3 Mini
On the cost-quality frontier for General LLM: nothing scores better…0d reign
Reasoning
DSGG
DeepSeek R1 & Gemini 3.1 Flash Lite & Gemini 4 Argon & Gemma 3 27B IT & GLM 4.5 Air & GPT-5 Mini & Kimi K2 5 & O3 Mini
On the cost-quality frontier for Reasoning: nothing scores better for…0d reign
Math
GGG
Gemini 3.1 Flash Lite & Gemini 3.1 Pro Preview & Gemini 3.8 Flash & GLM 4.5 Air & GPT-5 Mini & GPT-6 Astra & Kimi K2 5
On the cost-quality frontier for Math: nothing scores better for less…0d reign
Coding
ZZO
GLM 5.3 & GLM 5.3 Flash & GPT-5 & GPT-6 Luna
On the cost-quality frontier for Coding: nothing scores better for…0d reign
Coding › Agentic
AAZ
Claude Opus 5.5 & Claude Sonnet 5.5 & GLM 5.3 & GLM 5.3 Flash & GPT-6 Luna
On the cost-quality frontier for Coding › Agentic: nothing scores…0d reign
Coding › Web dev
AA
Claude Opus 5.5 & Claude Sonnet 5.5
On the cost-quality frontier for Coding › Web dev: nothing scores…0d reign
Long context
OKO
GPT-5 Mini & Kimi K2 5 & O3
On the cost-quality frontier for Long context: nothing scores better…0d reign
Vision
GOO
Gemini 3.7 Flash & GPT-5.6 Sol & GPT-6 Astra & GPT-6 Luna & Muse Spark 1.3
On the cost-quality frontier for Vision: nothing scores better for…0d reign
Image edit
G
Gemini Nano Banana 2.1
On the cost-quality frontier for Image edit: nothing scores better for…0d reign
Factuality
GXI
Gemini 4 Argon & Mimo V2.6 Pro
On the cost-quality frontier for Factuality: nothing scores better for…0d reign

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

Latest rulings

Crown changes

Full changelog →
General LLM: Gemini 2.5 Pro takes the crownGeneral LLM: GLM 5 takes the crownGeneral LLM: Kimi K3 takes the crownReasoning: Gemini 1.5 Pro 002 takes the crownReasoning: Gemini 2.5 Pro Exp 03.25 and O3 and O4 Mini and Gemini 2.5 Pro Preview 05.06 and Gemini 2.5 Pro Preview 06.05 are co-SOTAReasoning: O3 and Gemini 2.5 Pro Preview 06.05 and GPT-5 and GPT-5 Mini are co-SOTA
Awaiting evidence

Too early to call

GGemini 4 Argon
Google DeepMindPending

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

GET /v1/is-sota

REST API

One call, one dated answer. No key for normal use.

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. Rank, never a NOT-SOTA stamp.

RSS · email log

Alerts

RSS is live. Email is stored until a mail provider is connected.