Terminal-Bench 2.0
An agentic benchmark measuring whether an AI model can complete real command-line / terminal software tasks end-to-end (version 2.0, the 89-task set), scored by task success rate. Distinct from the newer Terminal-Bench 2.1 (a different task set); most 2026 model cards self-report this 2.0 version.
What this benchmark measures
An agentic benchmark measuring whether an AI model can complete real command-line / terminal software tasks end-to-end (version 2.0, the 89-task set), scored by task success rate. Distinct from the newer Terminal-Bench 2.1 (a different task set); most 2026 model cards self-report this 2.0 version.
Rows on this page are sourced from public benchmark artifacts, leaderboard exports, or source-linked model reports. Each row keeps benchmark version, source model name, and available run details attached to the score.
The metric shown here is task success. It should be interpreted within Terminal-Bench 2.0, not compared as part of a site-wide ranking.
Frequently asked
What is Terminal-Bench 2.0?
An agentic benchmark measuring whether an AI model can complete real command-line / terminal software tasks end-to-end (version 2.0, the 89-task set), scored by task success rate. Distinct from the newer Terminal-Bench 2.1 (a different task set); most 2026 model cards self-report this 2.0 version. It is a agents benchmark measured by task success.
What does task success mean on Terminal-Bench 2.0?
Terminal-Bench 2.0 reports task success (%); higher is better. Scores are shown only within Terminal-Bench 2.0 and are never averaged with other benchmarks.
What is the top reported Terminal-Bench 2.0 score?
Claude Fable 5 has the top reported score on Terminal-Bench 2.0: 84.3% (task success).
Why do Terminal-Bench 2.0 scores differ across runs?
Harness, scaffold, reasoning effort, and prompt setup change results, so two runs of the same model can differ. evals.report keeps each score with its run context so the differences stay visible.
Does evals.report rank models across benchmarks?
No. Terminal-Bench 2.0 scores are shown within their own metric; evals.report never combines benchmarks into a composite ranking or a single "best model".