AISOTA
EN中文
· State of the Art

Daily AI Decision Intelligence

Multi-source rankings blended into one score. See which model is truly State of the Art — today.

Data as of 2026-09-02Updated Sep 2, 11:09 AM

Overall Intelligence

Multi-source blend of general intelligence benchmarks into a single AISOTA score.

Sources:Artificial AnalysisLiveBench
#ModelArtificial AnalysisLiveBenchAISOTA Score
1SOTAClaude Fable 5.1 (max with fallback)2 sources95.098.096.5
22gpt-5.5-xhigh—92.292.2
33Claude Fable 5 (with fallback)2 sources85.096.190.5
4Claude Opus 5 (max)2 sources90.090.290.1
5GPT-5.6 Sol (max)2 sources80.094.187.0
6smaug-agentic—86.386.3
7qwen3.8-max—84.384.3
8Grok 4.6 (high)2 sources75.080.477.7
9gpt-5.4-xhigh—76.576.5
10Kimi K3 (max)2 sources70.082.476.2

Coding Ability

Multi-source blend of coding benchmarks into a single AISOTA score.

Sources:Artificial Analysis AgenticLiveBench Coding
#ModelArtificial Analysis AgenticLiveBench CodingAISOTA Score
1SOTAClaude Fable 5.1 (max with fallback)2 sources95.098.096.5
22smaug-agentic—96.196.1
33Claude Opus 5 (max)2 sources90.092.291.1
4GLM-5.3 (max)2 sources85.088.286.6
5qwen3.8-max—86.386.3
6claude-sonnet-5-xhigh-effort—84.384.3
7Claude Fable 5 (with fallback)2 sources60.094.177.0
8deepseek-v4-flash-vision-exp—76.576.5
9GPT-5.6 Sol (max)2 sources70.082.476.2
10qwen3.8-flash-next—74.574.5

Value for Money

Intelligence per dollar, based on median input + output price.

Sources:AA IntelligenceOpenRouter Price
#ModelAA IntelligenceOpenRouter PriceAISOTA Score
1SOTAGLM-5.3-Flash2 sources55.076.065.5
22Gemini 3.7 Flash (high)2 sources40.065.552.8
33GPT-5.6 Luna (max)2 sources30.074.752.4
4GPT-5.6 Sol (max)2 sources80.022.051.0
5Claude Opus 5 (max)2 sources90.010.550.3
6Claude Fable 5.1 (max with fallback)2 sources95.03.449.2
7Grok 4.6 (high)2 sources75.017.946.5
8Claude Fable 5 (with fallback)2 sources85.05.145.0
9GLM-5.3 (max)2 sources65.023.044.0
10Qwen3.8 2.4T A95B2 sources60.018.239.1

Model Usage

API request volume per model over the last 7 days, sourced from OpenRouter public rankings.

Sources:OpenRouter Usage
#ModelOpenRouter UsageAISOTA Score
1SOTAdeepseek-v4-flash921.99M99.8
22gpt-5-6-luna330M99.5
33gemini-2-5-flash-lite304.25M99.3
4glm-5-3-flash291.13M99.1
5gpt-oss-20b126.51M98.9
6gemini-3-1-flash-lite122.27M98.6
7gemini-2-5-flash120.76M98.4
8text-embedding-3-small120.54M98.2
9gpt-oss-120b117.98M97.9
10gpt-4o-mini110.74M97.7

AI Tools Leaderboard

Ranked lists of the best AI tools across the most popular categories, with editorial notes on each tool.

AI Compute & API Pricing

Live AI compute prices: model API inference costs, cloud GPU benchmark pricing, and best value models per quality point. Updated daily from public sources.

API Inference Pricing

2757 entries

  1. 1SOTAdeepinfra/meta-llama/Llama-3.2-3B-Instruct$0.02/M
  2. 2lambda_ai/llama3.2-3b-instruct$0.02/M
  3. 3nscale/Qwen/Qwen2.5-Coder-3B-Instruct$0.02/M
  4. 4nscale/Qwen/Qwen2.5-Coder-7B-Instruct$0.02/M
  5. 5nebius/Qwen/Qwen2.5-Coder-7B$0.02/M

Chinese AI Models Pricing

869 entries

  1. 1SOTAnscale/Qwen/Qwen2.5-Coder-3B-Instruct$0.02/M
  2. 2nscale/Qwen/Qwen2.5-Coder-7B-Instruct$0.02/M
  3. 3nebius/Qwen/Qwen2.5-Coder-7B$0.02/M
  4. 4nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B$0.03/M
  5. 5novita/qwen/qwen3-4b-fp8$0.03/M

Cloud GPU Benchmark Pricing

18 entries

  1. 1SOTAStandard_NV4as_v4$0.054/h
  2. 2Standard_NC36ds_xl_RTXPRO6000BSE_v6$0.333/h
  3. 3Standard_NV24s_v3$0.584/h
  4. 4Standard_NV16as_v4$1.901/h
  5. 5Standard_NC320lds_xl_RTXPRO6000BSE_v6$2.643/h

How AISOTA scoring works

Each model is scored against the sources on that board. Within each source, models are ranked and converted to a 0–100 percentile. A model's AISOTA score is the weighted average of its percentile ranks across sources. SOTA marks today's #1.

Data is collected automatically from public APIs each day. Missing cells mean the source does not list that model.