Benchmark

Terminal-Bench 3.0

Terminal-Bench 3.0 is a release of the Terminal-Bench benchmark that tests AI agents' ability to operate a computer via the terminal on real-world…

Modality
text
Categories
reasoning, agents, code, tool_calling
Openness
unknown
Source
llm_stats
Reported scores
3

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Gemini 3.7 FlashGoogle0.1492026-08-13evidence
GLM-5.3Z.ai0.2832026-08-14evidence
Grok 4.6xAI0.262026-08-12evidence

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.