LABBench2 is a public benchmark of nearly 1,900 tasks that measure practical biology research capabilities across literature understanding, biological database access, molecular biology, protocol troubleshooting and experiment planning in more realistic settings than the original LAB-Bench.
查看 LABBench2 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 | 82.10 | 2026-08-13 | 未知 | 闭源 |
Google reported an 82.1% aggregate score for Gemini 3.7 Flash with a Linux terminal, bioinformatics tools, Python, R and internet access in August 2026.
