Skip to main content

Benchmark profile

HealthBench raw score (HealthBench (raw))

Raw score on realistic multi-turn healthcare conversations graded against expert-written rubrics.

Data verified

Benchmark score on HealthBench (raw) — July 24, 2026

BenchLM mirrors the published score view for HealthBench (raw). Claude Opus 5 leads the public snapshot at 67.1%. BenchLM does not use these results to rank models overall.

1 modelKnowledgeCurrentDisplay onlyUpdated July 24, 2026

Benchmark score table (1 model)

Score
1
Claude Opus 5Anthropic · Closed
67.1%

About HealthBench (raw)

Year

2026

Tasks

5,000 multi-turn patient conversations

Format

Raw rubric score

Difficulty

Realistic healthcare conversations

Section 8.15.1 reports the unadjusted HealthBench score. This provider-run result is display-only and remains separate from the length-adjusted score.

BenchLM freshness & provenance

Version

HealthBench (raw) 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does HealthBench (raw) measure?

Raw score on realistic multi-turn healthcare conversations graded against expert-written rubrics.

Which model scores highest on HealthBench (raw)?

Claude Opus 5 by Anthropic currently leads with a score of 67.1% on HealthBench (raw).

How many models are evaluated on HealthBench (raw)?

1 AI models have been evaluated on HealthBench (raw) on BenchLM.

Last updated: July 24, 2026 · BenchLM version HealthBench (raw) 2026