Terminal Bench 2.0

Explore score history ↗

Terminal Bench 2.0 is an AI benchmark in the Benchmark Radar catalog.

Released: 2025-11-07
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

Terminal Bench 2.0 results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
Codex CLI	—	60.4	—	evidence
Droid (Claude Opus 4.5)	—	63.1	—	evidence
Letta Code (Claude Opus 4.5)	—	59.1	—	evidence
Warp	—	61.2	—	evidence
Warp	—	59.1	—	evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.

Which sources cite Terminal Bench 2.0?

Terminal Bench 2.0