Which AI model scores highest on HealthBench?

GPT-6 Sol by OpenAI holds the best HealthBench (consensus) result among tracked models, at 95.8% (released Sep 22 2026). Higher scores are better on this benchmark.

What are the top 5 models on HealthBench?

1. GPT-6 Sol (OpenAI) — 95.8%; 2. GPT-6 Luna (OpenAI) — 95.6%; 3. GPT-6 Astra (OpenAI) — 95.4%; 4. gpt-oss-120b (OpenAI) — 89.9%; 5. gpt-oss-20b (OpenAI) — 82.6%.

How many models have a published HealthBench score?

5 tracked models have a published HealthBench (consensus) 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 (consensus), scoring 89.9% at rank 4 overall.

Healthcare

HealthBenchconsensus

physician rubric score on the consensus subset 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 consensus subset of the original HealthBench evaluation
: GPT-6 Sol by OpenAI holds the best HealthBench (consensus) result among tracked models, at 95.8% (released Sep 22 2026). Higher scores are better on this benchmark.
: 1. GPT-6 Sol (OpenAI) — 95.8%; 2. GPT-6 Luna (OpenAI) — 95.6%; 3. GPT-6 Astra (OpenAI) — 95.4%; 4. gpt-oss-120b (OpenAI) — 89.9%; 5. gpt-oss-20b (OpenAI) — 82.6%.
: 5 tracked models have a published HealthBench (consensus) 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 (consensus), scoring 89.9% at rank 4 overall.