Frontierswe benchmark scores from Epoch AI's benchmark data collection.
Sourced from Epoch AI's systematic benchmark data collection covering frontier models.
Auto-generated definition — editorial description not yet written.
Higher is better.
Auto-generated definition — editorial description not yet written.
| # | Model | Score |
|---|---|---|
| 1 | Kimi K2.5 (Reasoning) | 11.7 |
| 2 | Qwen3.6 Plus | 11.3 |
| 3 | Gemini 3.1 Pro Preview | 11.0 |
| 4 | Kimi K2.6 | 9.3 |
| 5 | GLM-5.1 (Reasoning) | 8.7 |
| 6 | Claude Opus 4.7 | 4.7 |