Skip to main content
Benchmark Registry
ModelsBenchmarksOrganizationsCompare

Terminal-Bench

Benchmark
Terminal-Bench
Evaluated by
Terminal-Bench Team
Release date
May 6, 2026
Version
Terminal-Bench 2.1 — Terminus-2
Metric
Terminal-Bench Accuracy

Results

3 results

LatestHistory
All providersMeta AI (originally Facebook AI Research)MiniMaxZ.ai
Terminal-Bench 2.1 — Terminus-2 results
ProviderModelScoreSourceRegistry No.
Meta AI (originally Facebook AI Research)Muse Glimmer 30B (high)51.7%Source for Muse Glimmer 30B (high) on Terminal-Bench 2.1 — Terminus-2 (opens in a new tab)80004
Z.aiGLM-5.281.0%Source for GLM-5.2 on Terminal-Bench 2.1 — Terminus-2 (opens in a new tab)150004
MiniMaxMiniMax M366.0%Source for MiniMax M3 on Terminal-Bench 2.1 — Terminus-2 (opens in a new tab)140003
Page 1 of 1

© 2026 Densa Labs

Toggle between the data update date and the application build time.
Legal
Color theme