AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
Model reports
HealthBench Professional
A distinct, harder split from the HealthBench variants recorded separately in this registry, so its scores are not comparable to them. Published as an OpenAI paper (525 examples, 3 clinician use cases) with a public dataset; released 2026-04-22 per PDF metadata. Graded by an LLM against physician-written rubrics.
Evaluation context and evidence
- Source
- Model reports
- Publisher
- Not recorded
- Benchmark release
- 2026-04-22
- Collected
- Not recorded
- Modality
- Not recorded
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 0
This source record has no numeric results in our collection. That does not mean a score of zero or that no public results exist. Consult the original resources above.