overlooked-bench
Explore score history ↗Evaluates AI models on 91 items across five tracks: ethics and philosophy, niche academic domains, small-organisation tasks, education, and matched institutional-criticism prompts, using rubric-based scoring and cross-judge validation.
- Released
- 2026-09-07
- Evaluates
- General AI, Language & Knowledge, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
overlooked-bench code
No reported scores are on record for this benchmark yet.