Terminal-Bench 2.0 on deepseek-v3.2
89 tasks, 5 attempts, open network. Updated 25 Oct 2026.
Ranking
Pass rate by harness, higher is better
All harnesses
| Harness | pass^5 | Last published |
|---|---|---|
| Terminus 22.0.0 | 21.3% | 25 Oct 2026run #121 |
89 tasks, 5 attempts, open network. Updated 25 Oct 2026.
| Harness | pass^5 | Last published |
|---|---|---|
| Terminus 22.0.0 | 21.3% | 25 Oct 2026run #121 |