Which AI model scores highest on HealthBench?

gpt-oss-120b by OpenAI holds the best HealthBench (full set) result among tracked models, at 57.6% (released Aug 5 2025). Higher scores are better on this benchmark.

What are the top 5 models on HealthBench?

1. gpt-oss-120b (OpenAI) — 57.6%; 2. GPT-6 Astra (OpenAI) — 56.9%; 3. GPT-6 Luna (OpenAI) — 50%; 4. GPT-6 Sol (OpenAI) — 47.1%; 5. gpt-oss-20b (OpenAI) — 42.5%.

How many models have a published HealthBench score?

5 tracked models have a published HealthBench (full set) 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.

What is the best open model on HealthBench?

gpt-oss-120b by OpenAI is the highest-ranked model with downloadable weights on HealthBench (full set), scoring 57.6% at rank 1 overall.

Healthcare

HealthBenchfull set

physician rubric score on the full set of the original HealthBench evaluation

full set full set, length-adjusted hard hard, length-adjusted consensus consensus, length-adjusted

Rankings

Higher is better

HealthBench — frequently asked questions

: physician rubric score on the full set of the original HealthBench evaluation
: gpt-oss-120b by OpenAI holds the best HealthBench (full set) result among tracked models, at 57.6% (released Aug 5 2025). Higher scores are better on this benchmark.
: 1. gpt-oss-120b (OpenAI) — 57.6%; 2. GPT-6 Astra (OpenAI) — 56.9%; 3. GPT-6 Luna (OpenAI) — 50%; 4. GPT-6 Sol (OpenAI) — 47.1%; 5. gpt-oss-20b (OpenAI) — 42.5%.
: 5 tracked models have a published HealthBench (full set) 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.
: gpt-oss-120b by OpenAI is the highest-ranked model with downloadable weights on HealthBench (full set), scoring 57.6% at rank 1 overall.