HealthBench Professionallength-adjusted

The same physician-graded health conversations as HealthBench Professional, scored with an adjustment for how long the answer is — so a model cannot gain by padding its reply. The adjustment moves scores by several points, so these numbers are not interchangeable with the unadjusted ones. Higher is better.

GPT-6 Astra by OpenAI holds the best HealthBench Professional (length-adjusted) result among tracked models, at 63.4% (released Sep 3 2026). Higher scores are better on this benchmark.

1. GPT-6 Astra (OpenAI) — 63.4%.

1 tracked model has a published HealthBench Professional (length-adjusted) score. Scores are collected from published lab reports and benchmark sources, with recorded sources credited alongside the results. We do not re-run the evaluations.