ClarifyCodeBench
Explore score history ↗ClarifyCodeBench evaluates LLMs on clarifying ambiguous requirements for code generation through interactive dialogues. It includes manual annotations of ambiguity types, clarification questions, and ground-truth answers, with metrics for interaction quality.
- Released
- 2026-07-01
- Institutions
- Peking University
- Evaluates
- Code, Code & Software, Code generation, Software & AI Compute
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
ClarifyCodeBench paper and code
No reported scores are on record for this benchmark yet.