About BullshitBench v2
Definition and scoring
- Organisation
- Peter Gostev
- Category
- Reasoning
- Version
- 2025
- Direction
- higher is better
- Ranking use
- Reference
- Contamination risk
- Unknown
A benchmark that tests whether AI models challenge nonsensical, ill-posed, or logically flawed prompts instead of confidently generating incorrect answers. Measures the critical ability to push back on bad input. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗