Osworld 2 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 | Claude Opus 4.7 | 500.0 |
| 2 | MiniMax-M3 | 500.0 |
| 3 | GPT-5.5 (xhigh) | 500.0 |
| 4 | Kimi K2.6 | 500.0 |