Terminal Bench

Explore score history ↗

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

Released: 2025-05-19
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

Terminal Bench results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
Abacus AI Desktop	—	62.3	—	evidence
Ante	—	60.3	—	evidence
Apex2	—	64.5	—	evidence
Droid (claude-opus-4-1)	—	58.8	—	evidence
Droid (claude-sonnet-4-5)	—	57.5	—	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?

Terminal Bench