Benchmark profile
HealthBench raw score (HealthBench (raw))
Raw score on realistic multi-turn healthcare conversations graded against expert-written rubrics.
Data verifiedBenchmark 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.
Benchmark score table (1 model)
ScoreAbout 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
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.