Skip to content
Nightly Terminal-Bench

Nightly Terminal-Bench #50

Sign in to view logs

Nightly Terminal-Bench

Nightly Terminal-Bench #50

Run time

Learn about OS pricing on GitHub Actions
Job Run time
Determine models to test
4s
openai:gpt-5.1-codex / Run Terminal-Bench (openai:gpt-5.1-codex)
1h 9m 53s
anthropic:claude-sonnet-4-5 / Run Terminal-Bench (anthropic:claude-sonnet-4-5)
1h 12m 46s
2h 22m 43s