LLM Stats (HealthBench Professional): leaderboard
HealthBench Professional results as aggregated by LLM Stats, measuring performance on professional-level health and medical questions graded against physician-written rubrics.
Metric: Score (%). Source: llm-stats.com. Source: www-cdn.anthropic.com. Saturation forecast: Around January 2028. 17 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 5.5 | 69.2 | #11 |
| 2 | Claude Fable 5 | 66 | #16 |
| 3 | Claude Opus 5.5 | 65.6 | #3 |
| 4 | Claude Haiku 5.5 | 64.8 | #40 |
| 5 | GPT-6.1 Sol | 64.2 | #7 |
| 6 | GPT-6 Astra | 63.4 | #6 |
| 7 | Muse Wonder Full | 62.3 | #10 |
| 8 | GPT-5.6 Sol | 60.5 | #19 |
| 9 | Muse Wonder | 60.5 | #15 |
| 10 | Claude Opus 5 | 59.8 | #12 |
| 11 | Claude Sonnet 5 | 57.8 | #57 |
| 12 | GPT-5.6 Terra | 57.7 | #41 |
| 13 | Grok 4.7 | 56.7 | #25 |
| 14 | Claude Opus 4.8 | 55.8 | #37 |
| 15 | GPT-5.6 Luna | 55.7 | #68 |
No result here: #8 Gemini 4 Argon, #9 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-healthbench-professional · How It Works · Data refreshed daily, snapshot 2026-10-20.