End-to-End Environment Interaction on OSWorld-Verified (test)
61.4Pass@1
Claude-4.5-sonnet
Updated 3d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.12 | 61.4 | - | |
2025.12 | 47.5 | - | |
2025.12 | 43.9 | - | |
2025.12 | 42.5 | - | |
2025.12 | 40.2 | - | |
2025.12 | 37.7 | - | |
2025.12 | 37.2 | - | |
2025.12 | 34.9 | - | |
2025.12 | 34.1 | - | |
2025.12 | 33.9 | - | |
2025.12 | 31.9 | - | |
2025.12 | 30.3 | - | |
2025.12 | 27.4 | - | |
2025.12 | 26.2 | - | |
2025.12 | 24 | - | |
2025.12 | 23 | - | |
2025.12 | - | 40.4 | |
2025.12 | - | 48.5 |