AI Model Rankings
A curated leaderboard of leading AI models, scored from 0.00 to 0.99. Switch segments to rank for different users. See how scores are weighed on the methodology page.
A balanced blend of capability, reliability, speed and value.
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 0.95 |
| 2 | Sonnet 4.6 | 0.94 |
| 3 | Gemini 3 Flash | 0.92 |
| 4 | GPT 5.6 Mini | 0.82 |
| 5 | Mistral Large 3 | 0.82 |
| 6 | Haiku 4.5 | 0.81 |
| 7 | GPT 5.6 | 0.80 |
| 8 | Llama 4 405B | 0.80 |
| 9 | Grok 4 | 0.79 |
| 10 | Command R+ 2 | 0.77 |
| 11 | DeepSeek V4 | 0.76 |
| 12 | Opus 4.8 | 0.75 |