ContinuousBench
Explore score history ↗ContinuousBench evaluates differentially private synthetic text by measuring capability gain on QA sets derived from a new quarterly corpus (Geminon procedural data or News articles), with standardized training and evaluation harness.
- Released
- 2026-06-01
- Institutions
- Columbia University · New York University · Google (United States)
- Evaluates
- General AI, Language & Knowledge, cs.LG
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
ContinuousBench paper and code
No reported scores are on record for this benchmark yet.