Agent Task Execution on QWENCLAWBENCH
59.5Overall Score
Claude Opus 4.6
Updated 1mo ago
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
2026.06 | 59.5 | 57.8 | 57.3 | 55.6 | 48.5 | 54.3 | 76.8 | 67.3 | 71 | |
2026.06 | 58.7 | 63.1 | 53.3 | 58.8 | 39.4 | 49.4 | 75.7 | 66.9 | 70.8 | |
2026.06 | 57.4 | 56.2 | 52.2 | 55.1 | 46.6 | 56.1 | 76.9 | 62.6 | 67.5 | |
2026.06 | 56.7 | 55.2 | 54.3 | 57.9 | 38.4 | 52.6 | 70.6 | 71.1 | 63.7 | |
2026.06 | 56.5 | 57.1 | 49.1 | 57.3 | 46.4 | 53.4 | 74 | 60.6 | 64.9 | |
2026.06 | 51.9 | 51.6 | 51.5 | 50.7 | 39.3 | 46.3 | 62.2 | 60.2 | 59.8 | |
2026.06 | 50.7 | 45.5 | 46.8 | 49.7 | 35.6 | 57.1 | 63.8 | 63.7 | 60.7 | |
2026.06 | 50.5 | 46.6 | 46.5 | 53.7 | 40.6 | 54.2 | 62.7 | 51.7 | 58.7 | |
2026.06 | 44.91 | 32.3 | 43.3 | 60.2 | 14.2 | 28.4 | 70.9 | 78.4 | 50.1 | |
2026.06 | 41.7 | - | - | - | - | - | - | - | - | |
2026.06 | 41.29 | 35.8 | 46.1 | 46.7 | 7.8 | 33.2 | 51.5 | 61 | 54.1 | |
2026.06 | 38.7 | - | - | - | - | - | - | - | - | |
2026.06 | 34.5 | 26.6 | 39.9 | 58.8 | 15.4 | 19.9 | 33.2 | 30.2 | 44.8 | |
2026.06 | 31.5 | 24.3 | 28.8 | 34.2 | 15.4 | 34.3 | 48.3 | 55.4 | 24.4 | |
2026.06 | 15.84 | 12.7 | 15.9 | 18.2 | 5.8 | 9.4 | 22 | 34.3 | 13.3 | |
2026.06 | 12.85 | 13.5 | 10.2 | 21.9 | 2.9 | 10.1 | 11.3 | 23.3 | 7.2 | |
2026.06 | 11.5 | 17.3 | 7.9 | 13 | 2 | 14.2 | 13.1 | 9.3 | 10.7 | |
2026.06 | 7 | 6.6 | 10.8 | 7.1 | 0.8 | 7.2 | 2.5 | 6.3 | 13.2 |