Benchmark profile
HealthBench length-adjusted score (HealthBench (length-adjusted))
HealthBench score after applying a verbosity penalty to model responses.
Data verifiedBenchmark score on HealthBench (length-adjusted) — July 24, 2026
BenchLM mirrors the published score view for HealthBench (length-adjusted). Claude Opus 5 leads the public snapshot at 57.8%. BenchLM does not use these results to rank models overall.
Benchmark score table (1 model)
ScoreAbout HealthBench (length-adjusted)
Year
2026
Tasks
5,000 multi-turn patient conversations
Format
Length-adjusted rubric score
Difficulty
Realistic healthcare conversations
Section 8.15.1 reports the length-adjusted result separately from the raw score. All Claude models used max effort, no tools, and five trials.
BenchLM freshness & provenance
Version
HealthBench (length-adjusted) 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 (length-adjusted) measure?
HealthBench score after applying a verbosity penalty to model responses.
Which model scores highest on HealthBench (length-adjusted)?
Claude Opus 5 by Anthropic currently leads with a score of 57.8% on HealthBench (length-adjusted).
How many models are evaluated on HealthBench (length-adjusted)?
1 AI models have been evaluated on HealthBench (length-adjusted) on BenchLM.