Which AI model scores highest on HealthBench Professional?

Claude Opus 5.5 by Anthropic holds the best HealthBench Professional (raw) result among tracked models, at 77.1% (released Sep 22 2026). Higher scores are better on this benchmark.

What are the top 5 models on HealthBench Professional?

1. Claude Opus 5.5 (Anthropic) — 77.1%; 1. Claude Sonnet 5.5 (Anthropic) — 77.1%; 3. Claude Fable 5.1 (Anthropic) — 74.2%; 4. Claude Opus 5 (Anthropic) — 73.4%; 5. Claude Haiku 5.5 (Anthropic) — 71%.

How many models have a published HealthBench Professional score?

9 tracked models have a published HealthBench Professional (raw) score. Scores are collected from published lab reports and benchmark sources, with recorded sources credited alongside the results. We do not re-run the evaluations.

Health

HealthBench Professionalraw

physician-graded conversations, scored before adjustment for answer length

HealthBench Professional raw OpenAI grading, raw OpenAI grading, length-adjusted length-adjusted

Rankings

Higher is better

HealthBench Professional — frequently asked questions

: physician-graded conversations, scored before adjustment for answer length
: Claude Opus 5.5 by Anthropic holds the best HealthBench Professional (raw) result among tracked models, at 77.1% (released Sep 22 2026). Higher scores are better on this benchmark.
: 1. Claude Opus 5.5 (Anthropic) — 77.1%; 1. Claude Sonnet 5.5 (Anthropic) — 77.1%; 3. Claude Fable 5.1 (Anthropic) — 74.2%; 4. Claude Opus 5 (Anthropic) — 73.4%; 5. Claude Haiku 5.5 (Anthropic) — 71%.
: 9 tracked models have a published HealthBench Professional (raw) score. Scores are collected from published lab reports and benchmark sources, with recorded sources credited alongside the results. We do not re-run the evaluations.