DiscoBench
Explore score history ↗DiscoBench evaluates search agents on clarification-aware deep search, covering 211 samples and 463 ambiguity instances across 11 domains, with four ambiguity types, measuring task utility, ambiguity detection, interaction strategy, and cost efficiency.
- Released
- 2026-06-26
- Institutions
- Tsinghua Shenzhen International Graduate School · Tsinghua University
- Evaluates
- General AI, Language & Knowledge, Reasoning
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
DiscoBench paper
No reported scores are on record for this benchmark yet.