UnpredictaBench
Explore score history ↗UnpredictaBench evaluates whether language-model samples reproduce specified target distributions across statistical, program-induced, and natural-language random processes.
- Released
- 2026-06-04
- Institutions
- University of British Columbia
- Evaluates
- General AI, Language & Knowledge, cs.CL
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
UnpredictaBench paper
No reported scores are on record for this benchmark yet.