Long-horizon agentic tasks on BrowseComp-ZH Our Settings
71.3Pass@1
AgentSwing
Updated 19d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.03 | 71.3 | |
2026.03 | 70.2 | |
2026.03 | 69.9 | |
2026.03 | 69.2 | |
2026.03 | 66.8 | |
2026.03 | 66.8 | |
2026.03 | 62.4 | |
2026.03 | 61.6 | |
2026.03 | 58.1 | |
2026.03 | 56.7 | |
2026.03 | 53.9 | |
2026.03 | 50.1 | |
2026.03 | 49.1 | |
2026.03 | 47.3 | |
2026.03 | 47.1 | |
2026.03 | 45.2 | |
2026.03 | 43.3 | |
2026.03 | 42.9 | |
2026.03 | 40.1 | |
2026.03 | 38 | |
2026.03 | 33.6 | |
2026.03 | 31.5 | |
2026.03 | 30.8 | |
2026.03 | 28.4 | |
2026.03 | 15.6 |