HealthBench Professional (Mythos 5.1 System Card): leaderboard
HealthBench Professional: 525 physician-authored clinical conversations spanning consults, documentation and research tasks, graded against rubric criteria by an LLM judge; length-adjusted score in percent, higher is better. Anthropic's runs from Table 8.1.A of the Claude Fable 5.1 & Claude Mythos 5.1 System Card (September 2026); the Opus 5 cell LLM Stats mirrors is omitted.
Metric: Length-Adjusted Score (%). Source: www-cdn.anthropic.com. Saturation forecast: Around October 2027. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5 (Max) | 63.3 | #20 (Claude Fable 5) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=healthbench-professional-mythos-5-1-system-card · How It Works · Data refreshed daily, snapshot 2026-11-05.