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 2026-09-01Updated Sep 1, 11:07 AM

Overall Intelligence

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

Sources:Artificial AnalysisLiveBench
#ModelArtificial AnalysisLiveBenchAISOTA Score
1SOTAClaude Fable 5 (with fallback)2 sources90.098.094.0
22gpt-5.5-xhigh—94.094.0
33Claude Opus 5 (max)2 sources95.092.093.5
4GPT-5.6 Sol (max)2 sources85.096.090.5
5smaug-agentic—88.088.0
6qwen3.8-max—86.086.0
7Grok 4.6 (high)2 sources80.082.081.0
8Kimi K3 (max)2 sources75.084.079.5
9gpt-5.4-xhigh—78.078.0
10gemini-3.1-pro-preview-high—72.072.0

Coding Ability

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

Sources:Artificial Analysis AgenticLiveBench Coding
#ModelArtificial Analysis AgenticLiveBench CodingAISOTA Score
1SOTAsmaug-agentic—98.098.0
22Claude Opus 5 (max)2 sources95.094.094.5
33GLM-5.3 (max)2 sources90.090.090.0
4qwen3.8-max—88.088.0
5claude-sonnet-5-xhigh-effort—86.086.0
6Claude Fable 5 (with fallback)2 sources65.096.080.5
7GPT-5.6 Sol (max)2 sources75.084.079.5
8deepseek-v4-flash-vision-exp—78.078.0
9GLM-5.3-Flash2 sources80.072.076.0
10Kimi K3 (max)2 sources60.092.076.0

Value for Money

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

Sources:AA IntelligenceOpenRouter Price
#ModelAA IntelligenceOpenRouter PriceAISOTA Score
1SOTAGLM-5.3-Flash2 sources60.077.068.5
22Gemini 3.7 Flash (high)2 sources45.066.255.6
33GPT-5.6 Luna (max)2 sources35.075.755.4
4GPT-5.6 Sol (max)2 sources85.022.653.8
5Claude Opus 5 (max)2 sources95.011.153.0
6Grok 4.6 (high)2 sources80.018.949.5
7Claude Fable 5 (with fallback)2 sources90.05.747.9
8GLM-5.3 (max)2 sources70.023.646.8
9Kimi K3 (max)2 sources75.07.841.4
10Qwen3.8 2.4T A95B2 sources65.016.640.8

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-flash917.32M99.8
22gpt-5-6-luna328.14M99.5
33gemini-2-5-flash-lite312.71M99.3
4glm-5-3-flash233.42M99.1
5ox-alpha127.4M98.9
6gemini-3-1-flash-lite119.86M98.6
7gpt-oss-120b118.64M98.4
8gemini-2-5-flash116.61M98.2
9gpt-oss-20b116.19M97.9
10gpt-4o-mini114.1M97.7

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

2696 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

813 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.