ruby-skill-bench orchestrates evaluation runs of AI coding agents inside isolated git sandboxes, then scores the results using deterministic and LLM-powered judges.
Required Ruby Version
>= 3.1
Authors
Ismael Marin
Versions
- 1.4.0 September 14, 2026 (136 KB)
- 1.3.1 August 12, 2026 (133 KB)
- 1.3.0 August 08, 2026 (133 KB)
- 1.2.0 July 01, 2026 (131 KB)
- 1.1.0 June 23, 2026 (102 KB)