This BioMysteryBench subset contains the 76 tasks that at least one of up to five human domain experts solved correctly. It preserves the benchmark's real-world data analysis, terminal tools, bioinformatics software and restricted external data access conditions.
查看 BioMysteryBench (Human-solvable) 的最新得分、模型模式、发布时间与参数规模，快速了解当前完整榜单表现。
数据优先来自官方发布（GitHub、Hugging Face、论文），其次为评测基准官方结果，最后为第三方评测机构数据。 了解数据收集方法
| 排名 | 模型 | 开源情况 | |||
|---|---|---|---|---|---|
 Gemini 3.7 Flash 思考水平·中工具联网 | 87.10 | 2026-08-13 | 未知 | 闭源 |
Google reported 87.1% for Gemini 3.7 Flash on the BioMysteryBench human-solvable subset in August 2026.
