Agentic terminal task resolution on Terminal-Bench 2
83.14SSA Pass@1 Rate
Opus 4.6
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.06 | 83.14 | - | |
2026.06 | 80.67 | - | |
2026.06 | 79.1 | - | |
2026.06 | 76 | - | |
2026.06 | 75.05 | 77.3 | |
2026.06 | 74.6 | - | |
2026.06 | 74.15 | - | |
2026.06 | 73.93 | 65.4 | |
2026.06 | 73.7 | - | |
2026.06 | 72.58 | 75.1 | |
2026.06 | 72.35 | - | |
2026.06 | 72.13 | 68.5 | |
2026.06 | 68.76 | 64.7 | |
2026.06 | 66.29 | - | |
2026.06 | 65.39 | 59.8 | |
2026.06 | 64.71 | 59.1 | |
2026.06 | 63.59 | 47.6 | |
2026.06 | 62.69 | 62.2 | |
2026.06 | 56.4 | - | |
2026.06 | 56 | 59.3 | |
2026.06 | 54.83 | - | |
2026.06 | 52.35 | - | |
2026.06 | 50.78 | 41.6 | |
2026.06 | 49.21 | 51 | |
2026.06 | 48.76 | 51.5 | |
2026.06 | 43.37 | - | |
2026.06 | 42.47 | - | |
2026.06 | 41.8 | - | |
2026.06 | 41.57 | 41 | |
2026.06 | 38.87 | 36.2 | |
2026.06 | 36.17 | - | |
2026.06 | 35.73 | - | |
2026.06 | 30.11 | - | |
2026.06 | 17.07 | - |