# BioMysteryBench (hard) — AI model rankings

Real unsolved-style biology puzzles — the AI has to reason its way to an answer the way a research biologist would. The “hard” split contains the toughest cases. Higher is better.

3 tracked models have a published BioMysteryBench (hard) score. Higher is better. Scores are as published at each model's release.

## Ranking

| Rank | Model | Developer | Score | Source | Released |
| --- | --- | --- | --- | --- | --- |
| 1 | Gemini 3.8 Flash | Google | 56.5% | Lab | Sep 2 2026 |
| 2 | Claude Opus 5 | Anthropic | 49.4% | Lab | Jul 24 2026 |
| 3 | Gemini 3.7 Flash | Google | 43.5% | Lab | Aug 13 2026 |


---

Canonical page: https://aireleasetracker.com/benchmark/biomysterybench-hard
Full dataset: https://aireleasetracker.com/llms-full.txt · JSON: https://aireleasetracker.com/models.json
Source: AI Release Tracker (https://aireleasetracker.com). Benchmark scores are the figures published by the releasing lab at launch.