RandomBench
Explore score history ↗RandomBench evaluates whether multimodal LLMs maintain distributionally neutral behavior when selecting among equivalent options, providing metrics for entropy and distributional bias under explicit random instructions.
- Released
- 2026-06-04
- Evaluates
- General AI, Multimodal, Safety & Trustworthiness
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
RandomBench paper
No reported scores are on record for this benchmark yet.