Claude Opus 5 on HealthBench Professional
rank 3 of 9 · updated August 16, 2026
Claude Opus 5 scores 0.598 on HealthBench Professional, rank 3 of 9 evaluated models. Anthropic's frontier workhorse, priced at half of Claude Fable 5. HealthBench Professional scores models on 525 tasks drawn from real clinician conversations, graded criterion by criterion against physician-written rubrics on a 0 to 1 scale.
Result and API facts
| rank | 3 of 9 |
|---|---|
| score | 0.598 |
| lab | Anthropic |
| context window | 1.0M tokens |
| API price per 1M tokens | $5.00 in / $25.00 out |
| license | proprietary |
| released | 2026-07-24 |
Position in the field
The gap to the leader, Claude Fable 5 at 0.660, is 0.062. Directly above sits GPT-5.6 Sol at 0.605. Directly below sits Claude Sonnet 5 at 0.578. Scores on this page come from the same evaluation run, so differences between models are differences on identical tasks, not across configurations.
What does Claude Opus 5 score on HealthBench Professional?
Claude Opus 5 scores 0.598 on HealthBench Professional, which places it at rank 3 of 9 evaluated models as of August 16, 2026.
How much does Claude Opus 5 cost to run?
Claude Opus 5 is priced at $5.00 per million input tokens and $25.00 per million output tokens through Anthropic's API.
Head to head
Pairings with a dedicated comparison page are linked; every other difference is in the score-difference matrix.
- 0.598 vs 0.660 · Claude Fable 5 by 0.062
- 0.598 vs 0.605 · GPT-5.6 Sol by 0.007
- Claude Opus 5 vs Claude Sonnet 50.598 vs 0.578 · Claude Opus 5 by 0.020
- Claude Opus 5 vs GPT-5.6 Terra0.598 vs 0.577 · Claude Opus 5 by 0.021
- 0.598 vs 0.558 · Claude Opus 5 by 0.040
- Claude Opus 5 vs GPT-5.6 Luna0.598 vs 0.557 · Claude Opus 5 by 0.041
- Claude Opus 5 vs GPT-5.5 Instant0.598 vs 0.384 · Claude Opus 5 by 0.214
- Claude Opus 5 vs MAI-Thinking-10.598 vs 0.350 · Claude Opus 5 by 0.248
How tasks are selected and graded is on the methodology page. The full ranking is on the leaderboard.