Gbaeval 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 K2.6 | 133.0 |
| 2 | Kimi K2.7 Code | 100.0 |
| 3 | Qwen3.7 Max | 92.0 |
| 4 | MiniMax-M3 | 90.0 |
| 5 | Claude Opus 4.7 | 68.0 |
| 6 | Gemini 3.1 Pro Preview | 1.0 |
| 7 | MiniMax-M2.7 | 0.0 |
| 8 | GLM-5.1 (Reasoning) | 0.0 |