Skip to main content
Benchmark Registry
ModelsBenchmarksOrganizations

Terminal-Bench

Benchmark
Terminal-Bench
Evaluated by
Terminal-Bench Team
Release date
August 27, 2026
Version
Terminal-Bench Science 0.1
Metric
Terminal-Bench Accuracy

Results

6 results

LatestHistory
All providersAnthropicOpenAI
Terminal-Bench Science 0.1 results
ProviderModelScoreSourceRegistry No.
OpenAIGPT-6.1 Sol (low)43.7%Source for GPT-6.1 Sol (low) on Terminal-Bench Science 0.1 (opens in a new tab)10015
OpenAIGPT-6.1 Sol (high)51.1%Source for GPT-6.1 Sol (high) on Terminal-Bench Science 0.1 (opens in a new tab)10015
OpenAIGPT-6.1 Sol (medium)47.6%Source for GPT-6.1 Sol (medium) on Terminal-Bench Science 0.1 (opens in a new tab)10015
OpenAIGPT-6.1 Sol (xhigh)53.7%Source for GPT-6.1 Sol (xhigh) on Terminal-Bench Science 0.1 (opens in a new tab)10015
OpenAIGPT-6.1 Sol (max)57.0%Source for GPT-6.1 Sol (max) on Terminal-Bench Science 0.1 (opens in a new tab)10015
OpenAIGPT-6 Astra64.6%Source for GPT-6 Astra on Terminal-Bench Science 0.1 (opens in a new tab)10005
Page 1 of 1

© 2026 Densa Labs

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