AgentEvol-7B
| Method | Links | ||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2026.02 | 88 | 14 | 64 | 11.8 | 38 | 18.9 | 82.7 | 4.3 | 12 | 13.8 | 12 | 5.7 | 25 | 5.9 | 60 | 3.2 | 60.8 | 13 | |
2026.02 | 86.5 | 11 | 73 | 8.9 | 85.5 | 12.5 | 94.4 | 3.8 | 68 | 9.7 | 40 | 5.4 | 35 | 5.1 | 75 | 4 | 81 | 9.5 | |
2026.02 | 84.5 | - | 72 | - | 42 | - | 81 | - | 48 | - | 20 | - | 60 | - | 90 | - | 65.4 | - | |
2026.02 | 73 | 17.8 | 0 | 19.4 | 2.8 | 28.5 | 0.5 | 7.6 | 8 | 13.9 | 0 | 6 | 10 | 6.6 | 5 | 10.7 | 23.1 | 18.7 | |
2026.02 | 71 | 17.7 | 4 | 19.4 | 1.6 | 28.5 | 0.5 | 7.5 | 12 | 13.9 | 4 | 2 | 0 | 8.3 | 5 | 11.7 | 22.7 | 18.6 | |
2026.02 | 67.5 | 18.3 | 77 | 9.9 | 14.4 | 18.1 | 72.9 | 9.1 | 68 | 9 | 88 | 4 | 80 | 6 | 95 | 4.5 | 55.9 | 14.2 | |
2026.02 | 67 | 18.5 | 4 | 18.8 | 10.7 | 28.2 | 0.7 | 6.3 | 8 | 13.9 | 4 | 5.2 | 0 | 6.6 | 0 | 11.6 | 24 | 18.6 | |
2026.02 | 51 | 20.4 | 23 | 15.1 | 16.8 | 20.7 | 45.7 | 11.7 | 4 | 14.5 | 24 | 5.2 | 70 | 6.1 | 70 | 5.9 | 34.5 | 16.9 | |
2026.02 | 13 | 27.9 | 38 | 14.6 | 2.8 | 28.7 | 79.3 | 6.6 | 0 | 15 | 36 | 5.2 | 65 | 6.9 | 80 | 5.1 | 26.3 | 20.8 | |
2026.02 | 3.5 | 19.6 | 0 | 16.5 | 0.8 | 21.3 | 0.1 | 10.9 | 0 | 13.4 | 0 | 6 | 0 | 10 | 0 | 12 | 1.3 | 17.3 | |
2026.02 | 2 | 22.6 | 0 | 14.5 | 0.8 | 27.5 | 0.2 | 9.5 | 0 | 15 | 0 | 6 | 0 | 9.9 | 0 | 12 | 0.9 | 19.5 |