HyperAI
Command Palette
Search for a command to run...
HealthBench
OpenAI HealthBench：5,000 段健康对话，按医生编写的评分标准打分，涵盖从急诊转诊到全球健康的场景。
- 模型
- 15 当前，19 总共
- 中位数
- 58.5%
- 范围
- 48.4%–62.1%
| 排名 | 比较 | 模型 | 评分 |
|---|---|---|---|
| 1 | 62.1% | ||
| 2 | 60.4% | ||
| 3 | 60.2% | ||
| 4 | 59.8% | ||
| 5 | 59.7% | ||
| 6 | 59.6% | ||
| 7 |  GPT-6.1 Sol (Max) OpenAI | 58.5% | |
| 8 |  Claude Haiku 5.5 (Max) Anthropic | 58.5% | |
| 9 | GPT-6 Astra (Max) OpenAI | 58.2% | |
| 10 | 57.0% | ||
| 11 |  Grok 4.7 (Xhigh) SpaceXAI | 56.0% | |
| 12 | GPT-6 Luna (Max) OpenAI | 54.6% | |
| 13 |  GLM-5.3 (Max) Z AI | 54.5% | |
| 14 |  Gemini 4 Argon (High) Google | 49.1% | |
| 15 | Gemini 3.8 Flash (High) Google | 48.4% |