Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Terminal task resolution on Terminal-Bench 1.1 (test)

39Resolution Rate

Codex CLI

35.8836.6937.538.31May 7, 2026
Updated 23d ago

Evaluation Results

MethodLinks
2026.05
3946.960.54951.14
2026.05
3625.720.5496.96