Software Engineering Task Resolution on SWE-bench Verified
73.3Resolution Rate
TACT-GATE
Updated 2mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.05 | 73.3 | - | 65.3 | |
2026.05 | 73 | - | 67.5 | |
2026.05 | 70.5 | - | 116.4 | |
2026.05 | 69.1 | - | 55.7 | |
2026.05 | 68.4 | - | 73.1 | |
2026.05 | 67.9 | - | 75.8 | |
2026.05 | 67 | - | 75.2 | |
2026.05 | 66.2 | - | 78 | |
2026.05 | 65.5 | - | 44.7 | |
2026.05 | 65.2 | - | 46.2 | |
2026.05 | 62 | - | 78.9 | |
2026.05 | 61.6 | - | 38.6 | |
2026.05 | 61 | - | 52.5 | |
2026.05 | 60.4 | - | 51 | |
2026.05 | 60 | - | 53.2 | |
2026.05 | 59.7 | - | 52.1 | |
2025.09 | 57.4 | 19.8 | - | |
2025.09 | 54 | 21.1 | - | |
2025.09 | 53.4 | 21 | - | |
2025.09 | 38.8 | 27.5 | - | |
2026.05 | 36.6 | - | - | |
2025.09 | 35.4 | 30.7 | - | |
2026.05 | 34.4 | - | - | |
2025.09 | 34.2 | 30.3 | - | |
2026.05 | 32.2 | - | - | |
2026.05 | 30.9 | - | - | |
2026.05 | 29.8 | - | - | |
2026.05 | 28.5 | - | - | |
2026.05 | 27.3 | - | - | |
2026.05 | 27.3 | - | - | |
2026.05 | 26.2 | - | - | |
2026.05 | 24.5 | - | - | |
2026.05 | 23.4 | - | - | |
2026.05 | 23.4 | - | - | |
2026.05 | 22.9 | - | - | |
2026.05 | 20.6 | - | - | |
2026.05 | 19 | - | - | |
2026.05 | 15.2 | - | - | |
2026.05 | 14.6 | - | - | |
2026.05 | 11.6 | - | - | |
2026.05 | 11.2 | - | - | |
2026.05 | 10.6 | - | - | |
2026.05 | 9.4 | - | - | |
2026.05 | 8.2 | - | - | |
2026.05 | 7.7 | - | - | |
2026.05 | 7 | - | - | |
2025.12 | 0.704 | - | - | |
| 0.696 | - | - | ||
2025.12 | 0.668 | - | - | |
2025.12 | 0.624 | - | - | |
2025.12 | 0.576 | - | - | |
2025.12 | 0.532 | - | - | |
2025.12 | 0.53 | - | - | |
2025.12 | 0.516 | - | - | |
2025.12 | 0.508 | - | - | |
2025.12 | 0.498 | - | - | |
2025.12 | 0.492 | - | - | |
2025.12 | 0.474 | - | - | |
2025.12 | 0.468 | - | - | |
2025.12 | 0.46 | - | - | |
2025.12 | 0.42 | - | - | |
2025.12 | 0.388 | - | - | |
2025.12 | 0.23 | - | - |