OSWorld 2.0
Agents · 2026-06-25
OSWorld 2.0 evaluates computer-use agents on 108 long-horizon real-world workflows spanning everyday and professional desktop/web tasks. The official leaderboard reports binary completion accuracy and partial score under fixed step budgets.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-5.6 Sol | 62.6 |
| GPT-5.6 Terra | 50.2 |
| Opus 4.8 | 49.7 |
| GPT-5.5 | 47.5 |
| GPT-5.6 Luna | 45.6 |
| Opus 4.7 | 18.2 |
| Sonnet 4.6 | 9.3 |
| MiniMax M3 | 4.6 |
| Qwen3.7-Plus | 2.8 |