Benchmark
HealthBench
healthcare
text
An open-source benchmark for measuring performance and safety of large language models in healthcare, consisting of 5,000 multi-turn conversations evaluated by 262 physicians using 48,562 unique rubric criteria across health contexts and behavioral dimensions
语言EN
满分1
参评模型2
模型排名
| 名次 | 模型 | 机构 | 分数 | 来源 |
|---|---|---|---|---|
| 1 | GPT OSS 120B | OpenAI | 57.6 | 来源 ↗ |
| 2 | GPT OSS 20B | OpenAI | 42.5 | 来源 ↗ |