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.
Weighted toward reliability, security, deep reasoning and large context.
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 0.98 |
| 2 | Sonnet 4.6 | 0.95 |
| 3 | Gemini 3 Flash | 0.88 |
| 4 | Opus 4.8 | 0.87 |
| 5 | GPT 5.6 | 0.82 |
| 6 | Llama 4 405B | 0.80 |
| 7 | Mistral Large 3 | 0.79 |
| 8 | Grok 4 | 0.77 |
| 9 | Command R+ 2 | 0.77 |
| 10 | Haiku 4.5 | 0.75 |
| 11 | GPT 5.6 Mini | 0.75 |
| 12 | DeepSeek V4 | 0.72 |