terminal-bench@2.0 Leaderboard
harbor run -d terminal-bench@2.0 -a "agent" -m "model" -k 5harbor run -d terminal-bench@2.0 --agent-import-path "path.to.agent:SomeAgent" -k 5Showing 2 entries
Select agents
GPT-5.3-Codex
Select organizations
Verified only
| Rank | Agent | Model | Date | Agent Org | Model Org | Accuracy | |
|---|---|---|---|---|---|---|---|
9 | Simple Codex | GPT-5.3-Codex | 2026-02-06 | OpenAI | OpenAI | 75.1%± 2.4 | |
25 | Terminus 2 | GPT-5.3-Codex | 2026-02-05 | Terminal-Bench | OpenAI | 64.7%± 2.7 |
Results in this leaderboard correspond to terminal-bench@2.0.
Submission instructions can be found at harborframework/terminal-bench-2-leaderboard
A Terminal-Bench team member ran the evaluation and verified the results.
Displaying 2 of 124 available entries