Terminal-Bench 2.0 on Claude Opus 4.6

89 tasks, 5 attempts, open network. Updated 25 Oct 2026.

Every published run on this board, each with its own pass rate over the board's tasks, beside its configuration's pooled score.

Every run's pass rate

Pass rate, higher is better.

HarnessRuns, 0 to 100%PooledRuns

pilot82.0%74.2–88.51

meta-harness1.1.076.4%69.2–83.41

maya-v21.5-official71.9%63.4–79.61

Judy0.7.071.9%63.8–79.31

droid69.9%61.8–77.31

wozcode2.1.8668.1%60.0–76.41

Terminus 22.0.062.9%54.4–70.81

Copilot CLI60.4%51.5–68.81