Benchmark
DiscoBench
What is DiscoBench?
DiscoBench evaluates search agents on clarification-aware deep search, covering 211 samples and 463 ambiguity instances across 11 domains, with four ambiguity…
- Released
- 2026-06-26
- Evaluates
- General AI, Language & Knowledge, Reasoning
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2606.27669
DiscoBench paper
No reported scores are on record for this benchmark yet.