HealthBench Professional
based on the HealthBench Professional leaderboard, updated November 2, 2026

The best AI model for healthcare, November 2026

Measured on 525 physician-graded clinical tasks, Claude Fable 5 is the strongest model for professional healthcare work right now, at a length-adjusted score of 0.660. Its score before the length adjustment is 0.703. It is also the most expensive, and the right pick changes with the constraint you are actually under, so the table below answers the question four ways. The numbers come from the HealthBench Professional leaderboard, which this site compiles from published vendor documents and leaderboards; each row links to its source.
0.660
Claude Fable 5 length-adjusted score
0.703
Score before the length adjustment
525
physician-graded clinical tasks

The short version

NeedModelWhyScore before the length adjustment
Highest score, price no objectClaude Fable 5Length-adjusted score 0.660, ahead of the field by 0.055. $10.00 / $50.00 per 1M tokens.
Claude Fable 5: 0.703
The $4 tierGPT-5.6 Sol or Claude Opus 5Length-adjusted score 0.605 vs 0.598, a 0.007 gap that reads as a tie. GPT-5.6 Sol's output tokens are $5 per 1M cheaper.
GPT-5.6 Sol: 0.641
Claude Opus 5: 0.734
The $2 tierClaude Sonnet 5 or GPT-5.6 TerraLength-adjusted score 0.578 vs 0.577, 0.001 apart. Claude Sonnet 5's output tokens are $2 per 1M cheaper.
Claude Sonnet 5: 0.624
GPT-5.6 Terra: 0.624
High volume on a budgetGPT-5.6 LunaLength-adjusted score 0.557 at $0.20 / $1.20 per 1M tokens, within 0.103 of the leader at a fraction of every other price on the board.
GPT-5.6 Luna: 0.598

Why these picks

The top of the board splits into price tiers, and inside two of them the scores are effectively tied: 0.007 separates the $4-tier pair and 0.001 separates the $2-tier pair, both smaller than the differences that grader version or reasoning effort alone can introduce between 2 published numbers. That makes the honest recommendation at those tiers a toss-up settled by output pricing and your existing stack, not by the benchmark. The two decisions the benchmark does settle: Claude Fable 5's lead over everything else is real, and GPT-5.6 Luna delivers most of the field's capability for about a twenty-fifth of the $4-tier input price.

Where are the open-weights models?

Every model currently on the board ships behind a proprietary API; no open-weights model has a published HealthBench Professional result on this board yet. When one is added, this page will carry a pick for deployments that require local weights, which is a common constraint for health systems handling records on-premises.

What this page is not

A benchmark score measures rubric adherence on hard, written tasks. It does not measure bedside judgment, integration effort, latency, or whether a vendor will sign the agreements your compliance team needs, and none of it is medical advice. Read the methodology before treating any single number as a procurement decision, and read the benchmark page to understand what the tasks actually contain.