Blind-Spots-Bench
Explore score history ↗Evaluates reasoning blind spots in language, vision-language, and image-generation models across 235 samples with structured reference solutions and taxonomy.
- Released
- 2026-07-09
- Institutions
- École Polytechnique Fédérale de Lausanne
- Evaluates
- General AI, Multimodal
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
Blind-Spots-Bench paper and code
No reported scores are on record for this benchmark yet.