Knowledge benchmark
BioMysteryBench (human-difficult) leaderboard
BioMysteryBench Human Difficult. Every model the catalog carries a published BioMysteryBench (human-difficult) value for, ranked by that value.
Computational biology challenges with objective answers that remained unsolved by independent human experts.
BioMysteryBench (human-difficult) ranking
4 models with a published BioMysteryBench (human-difficult) value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Task score |
|---|---|---|---|
| 1 |  Gemini 3.8 Flash | 56.5 | |
| 2 |  Claude Opus 5 | Anthropic | 49.4 |
| 3 | Gemini 3.7 Flash | 43.5 | |
| 4 | APApodex 1.1 | Apodex | 35.3 |
Evidence key: Observed
Rows are ordered by the value Claude Opus 5 System Card published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.