BBQ Benchmark
Explore score history ↗Multiple-choice social-bias question answering (arXiv:2608.17183, §3.1). Scored by accuracy, unlike the ternary-judged suites in the same paper, so its numbers are not comparable with theirs. No per-model scores filed: the paper reports ambiguity and rank instability rather than benchmark scores.
- Evaluates
- knowledge
- Openness
- unknown
- Importer
- Model reports
No reported scores are on record for this benchmark yet.