Skip to main content
Benchmark Registry
ModelsBenchmarksOrganizationsCompare

Terminal-Bench

Benchmark
Terminal-Bench
Evaluated by
Terminal-Bench Team
Release date
November 7, 2025
Version
Terminal-Bench 2.0
Metric
Terminal-Bench Accuracy

Results

6 results

LatestHistory
All providersAnthropicCursorDeepSeek AIGoogle (DeepMind)Meta AI (originally Facebook AI Research)Microsoft AIMiniMaxMistral AIMoonshot AINVIDIAOpenAIZ.ai
Terminal-Bench 2.0 results
ProviderModelScoreSourceRegistry No.
DeepSeek AIDeepSeek-V4-Flash (high)56.6%Source for DeepSeek-V4-Flash (high) on Terminal-Bench 2.0 (opens in a new tab)110001
DeepSeek AIDeepSeek-V4-Flash (non-thinking)49.1%Source for DeepSeek-V4-Flash (non-thinking) on Terminal-Bench 2.0 (opens in a new tab)110001
DeepSeek AIDeepSeek-V4-Flash (max)56.9%Source for DeepSeek-V4-Flash (max) on Terminal-Bench 2.0 (opens in a new tab)110001
DeepSeek AIDeepSeek-V4-Pro (high)63.3%Source for DeepSeek-V4-Pro (high) on Terminal-Bench 2.0 (opens in a new tab)110002
DeepSeek AIDeepSeek-V4-Pro (non-thinking)59.1%Source for DeepSeek-V4-Pro (non-thinking) on Terminal-Bench 2.0 (opens in a new tab)110002
DeepSeek AIDeepSeek-V4-Pro (max)67.9%Source for DeepSeek-V4-Pro (max) on Terminal-Bench 2.0 (opens in a new tab)110002
Page 1 of 1

© 2026 Densa Labs

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