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

3 results

LatestHistory
All providersAnthropicOpenAI
Terminal-Bench Science 0.1 results
ProviderModelScoreSourceRegistry No.
AnthropicClaude Sonnet 5.5 (max)59.9%Source for Claude Sonnet 5.5 (max) on Terminal-Bench Science 0.1 (opens in a new tab)20016
AnthropicClaude Opus 5.5 (adaptive thinking, max)58.7%Source for Claude Opus 5.5 (adaptive thinking, max) on Terminal-Bench Science 0.1 (opens in a new tab)20015
AnthropicClaude Fable 5.152.6%Source for Claude Fable 5.1 on Terminal-Bench Science 0.1 (opens in a new tab)20004
Page 1 of 1

© 2026 Densa Labs

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