Updated daily at 05:00 UTC
Benchmark
ZeroBench
Measures: 100 hand-built, adversarially filtered visual reasoning questions (plus 334 subquestions) that were designed to be impossible for multimodal models at release; each question is sampled 5 times and scored by pass@5, pass^5 (all 5 right) and mean pass@1.
- Maintainer
- Jonathan Roberts et al. (maintained by Jonathan Roberts)
- Introduced
- 2025
- Status
- Active
- Saturation
- Headroom
- Typical provenance
- Mixed
- In scoring set
- Yes
Leaderboard
Independent and third-party results only.
No independent or third-party results yet. Show all results