Which AI model scores highest on HealthBench Professional?

Claude Fable 5 by Anthropic holds the best HealthBench Professional result among tracked models, at 63.3% (released Jun 9 2026). Higher scores are better on this benchmark.

What are the top 3 models on HealthBench Professional?

1. Claude Fable 5 (Anthropic) — 63.3%; 2. Claude Fable 5.1 (Anthropic) — 62.1%; 3. Claude Opus 5 (Anthropic) — 59.8%.

How many models have a published HealthBench Professional score?

3 tracked models have a published HealthBench Professional score. Scores are the figures reported by each lab at that model's release, so this page is a record of results over time rather than a re-run leaderboard.

Health

HealthBench Professional

Realistic health conversations graded against detailed rubrics written by physicians — can the AI respond the way a careful medical professional would? Higher is better.

HealthBench Professional length-adjusted

Rankings

Higher is better

HealthBench Professional — frequently asked questions

: Realistic health conversations graded against detailed rubrics written by physicians — can the AI respond the way a careful medical professional would? Higher is better.
: Claude Fable 5 by Anthropic holds the best HealthBench Professional result among tracked models, at 63.3% (released Jun 9 2026). Higher scores are better on this benchmark.
: 1. Claude Fable 5 (Anthropic) — 63.3%; 2. Claude Fable 5.1 (Anthropic) — 62.1%; 3. Claude Opus 5 (Anthropic) — 59.8%.
: 3 tracked models have a published HealthBench Professional score. Scores are the figures reported by each lab at that model's release, so this page is a record of results over time rather than a re-run leaderboard.