Coding
Terminal-Bench 2.1
The 2.1 revision of the terminal agent benchmark. Scores on it are not comparable with Terminal-Bench 4.0 — the task set changed.
Terminal-Bench 2.1 is scored as a percentage of questions answered correctly. 1 of the 159 models in this index report a score for it. The highest published figure here is 89.1%, from Claude Opus 5.
Reported scores
Top 1 on Terminal-Bench 2.1
Ordered by the figure each maker published. Models that have not reported this benchmark are not listed — an absent score is not a low score.
| # | Model | Published score |
|---|---|---|
| 1 | Claude Opus 5Anthropic |
Where these numbers come from
Every score on this page is a published figure, taken from the model's own card, system card, technical report or release post, or from a public leaderboard. CorX Labs did not run these evaluations. Most are self-reported by the lab that built the model, which means they were produced under that lab's own choice of prompt, scaffold and number of attempts — so treat them as a starting point for a shortlist, not as a settled ranking.
A score someone other than the model's maker measured is marked Independent and names its measurer. Those are the stronger numbers on this page — an outside harness has no reason to flatter anyone — and there are not many of them.
Where a figure has not been published, the cell reads Not reported rather than an estimate. Nothing here is inferred, interpolated or guessed. Each model records the month its row was last checked. Full method and caveats.
How to read this score
The 2.1 task set of Terminal-Bench. It is the version most third-party runs used through 2026, which makes it the one place several frontier models can be compared on a harness nobody selling a model controls.
Where it is weak
Do not read it against Terminal-Bench 4.0. The task set changed between versions, so a 2.1 score and a 4.0 score are different measurements that happen to share a name.