ExplainBench
Explore score history ↗Evaluates code explanations from agents by checking whether explanations enable an LLM to correctly answer questions about intended behavior and patch effects, using a question-based suite derived from agent patches.
- Released
- 2026-07-29
- Evaluates
- Code & Software, Software & AI Compute, cs.SE
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
ExplainBench paper and code
No reported scores are on record for this benchmark yet.