HealthBench raw score (HealthBench (raw))
We show this table for reference; we do not rank on it.
Raw score on realistic multi-turn healthcare conversations graded against expert-written rubrics.
Benchmark score on HealthBench (raw) — September 27, 2026
We compile the HealthBench (raw) rows from provider self-reports. Claude Opus 5.5 leads the table at 68.1%, followed by Claude Opus 5 (67.1%) and GPT-6 Astra (56.9%). We do not use these results to rank models overall.
Claude Opus 5.5
Anthropic
Claude Opus 5
Anthropic
GPT-6 Astra
OpenAI
5 modelsKnowledgeCurrentDisplay onlyUpdated September 27, 2026
Benchmark score table (5 models)
ScoreAmong the reported HealthBench (raw) rows, Claude Opus 5.5 is first at 68.1%. The third row is 11.2 points behind. The broader top-10 range is 21.0 points, so the table still separates the published systems.
5 models have been evaluated on HealthBench (raw). The benchmark falls in the Knowledge category. HealthBench (raw) is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
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.
Freshness and 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.
Questions
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 5.5 by Anthropic currently leads with a score of 68.1% on HealthBench (raw).
How many models are evaluated on HealthBench (raw)?
5 AI models have been evaluated on HealthBench (raw) on BenchLM.
Compare top models on HealthBench (raw)
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 2,000+ readers.
One email each week. Unsubscribe anytime.