Compare AI models
across real-world tasks.

1. 1✳Claude Opus 5.5 (Max)Anthropic17.18%726,932 observations
2. 2◉GPT 6.1 Sol (Max)OpenAI14.78%934,048 observations
3. 3✳Claude Fable 5.1 (Max)Anthropic14.12%1,876,054 observations
4. 4GGemini 4 Argon (High)Google13.73%2,404,951 observations
5. 5◉GPT 6 Astra (Max)OpenAI13.69%963,166 observations
6. 6✳Claude Sonnet 5.5 (Max)Anthropic12.55%907,789 observations
7. 7◉GPT 6 Sol (Max)OpenAI11.2%1,163,820 observations
8. 8✳Claude Opus 5 (Max)Anthropic9.2%3,089,208 observations
9. 9✳Claude Fable 5 (High)Anthropic8.39%2,503,647 observations
10. 10◉GPT 5.6 Sol (xHigh)OpenAI7.42%4,363,991 observations

Published source ranks are retained. Bar lengths help compare entries within this ranking; metrics from different use cases are not combined.