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 2026-09-08Updated Sep 8, 05:00 PM

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 sources95.098.296.6
22GPT-6 Astra (max)2 sources90.094.692.3
33gpt-5.5-xhigh—89.389.3
4Claude Fable 5 (with fallback)2 sources80.096.488.2
5Claude Opus 5 (max)2 sources85.087.586.3
6gemini-3.7-flash-high—85.785.7
7Muse Spark 1.3 (max)2 sources75.092.984.0
8smaug-agentic—83.983.9
9qwen3.8-max—82.182.1
10GPT-5.6 Sol (max)2 sources70.091.180.5

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-effort—98.298.2
22smaug-agentic—96.496.4
33claude-fable-5-max-effort—94.694.6
4claude-opus-5-max-effort—92.992.9
5muse-spark-1.3-xhigh—91.191.1
6kimi-k3—89.389.3
7glm-5.3—87.587.5
8qwen3.8-max—85.785.7
9claude-sonnet-5-xhigh-effort—83.983.9
10smaug-flash—82.182.1

Value for Money

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

Sources:AA IntelligenceOpenRouter Price
#ModelAA IntelligenceOpenRouter PriceAISOTA Score
1SOTAGLM-5.3-Flash2 sources45.075.860.4
22GPT-5.6 Luna (max)2 sources30.074.552.3
33Claude Fable 5.1 (max with fallback)2 sources95.05.050.0
4Muse Spark 1.3 (max)2 sources75.024.849.9
5Claude Opus 5 (max)2 sources85.010.948.0
6GPT-6 Astra (max)2 sources90.05.647.8
7GPT-5.6 Sol (max)2 sources70.022.246.1
8GLM-5.3 (max)2 sources65.023.244.1
9Gemini 3.8 Flash (high)2 sources40.047.043.5
10Claude Fable 5 (with fallback)2 sources80.04.642.3

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-flash1.02B99.8
22gpt-5-6-luna499.69M99.5
33glm-5-3-flash341.07M99.3
4gemini-2-5-flash-lite248.29M99.1
5hy4152.02M98.9
6gemini-3-1-flash-lite136.81M98.6
7gemini-2-5-flash133.37M98.4
8text-embedding-3-small123.63M98.2
9gpt-4o-mini111.08M98.0
10gpt-oss-120b105.49M97.7

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

2980 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

952 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.