terminal-bench@2.1 Leaderboard
harbor run -d terminal-bench/terminal-bench-2-1 -a "agent" -m "model" -k 5harbor run -d terminal-bench/terminal-bench-2-1 --agent-import-path "path.to.agent:SomeAgent" -k 5harbor run -d terminal-bench/terminal-bench-2-1 -a "agent" -m "model" -k 5harbor run -d terminal-bench/terminal-bench-2-1 --agent-import-path "path.to.agent:SomeAgent" -k 5| Rank | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 3 | high | 80.4% ± 1.2% | Jun 5, 2026 | $438.64 | ||||||
| 7 | xhigh | 78.0% ± 1.2% | May 1, 2026 | $493.85 | ||||||
| 11 | high | 73.9% ± 1.3% | May 1, 2026 | $224.44 | ||||||
| 13 | max | 66.1% ± 1.4% | May 1, 2026 | $582.26 | ||||||
| 16 | high | 65.6% ± 1.7% | May 5, 2026 | $229.99 |
Results in this leaderboard correspond to terminal-bench/terminal-bench-2-1.
Submit via the terminal-bench-2-1 repo.
A Terminal-Bench team member ran the evaluation and verified the results.
Displaying 5 of 17 available entries