window-close on ContinualBench window-close
72.6Success Rate
ProgAgent
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.03 | 72.6 | 74.1 | 26.2 | |
2026.03 | 72.4 | 61.8 | 30.8 | |
2026.03 | 71.9 | 73.1 | 31 | |
2026.03 | 68.4 | 72.9 | 27.6 | |
2026.03 | 65.2 | 55.8 | 31.6 | |
2026.03 | 61.7 | 50.2 | 32.1 | |
2026.03 | 56.4 | 45.3 | 33 | |
2026.03 | 50.1 | 40 | 33.6 | |
2026.03 | 35.8 | 24.9 | 37.7 |