InteractBench
Explore score history ↗InteractBench evaluates LLM code generation on interactive competitive programming problems where solutions must query a judge to obtain hidden information under protocol constraints.
- Released
- 2026-08-30
- Institutions
- Huazhong University of Science and Technology
- Evaluates
- Code & Software, Code generation, General AI, cs.SE
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
InteractBench paper and code
No reported scores are on record for this benchmark yet.