Clinical Benchmarks

OpenAI logoGPT OSS 20B: healthcare benchmark results

OpenAI · 2 boards · updated September 8, 2026

The index currently holds 2 results for GPT OSS 20B: 0.108 on HealthBench Hard (16 of 16 indexed rows), 42.5 on HealthBench (18 of 18 indexed rows). Scores below sit on different scales and come from different graders, so read each against its own benchmark, never against the others.

Results by benchmark

benchmarkscoreindex positionas of
HealthBench Hard0.10816 of 162025-08
HealthBench42.518 of 182025-08

Position follows the rows held in this index, including separate configurations. A source board may contain additional rows; its size is listed separately when it differs. Config caveats, where a source noted any, are on each benchmark's page, and the document behind each score is cited on the sources page.

Which healthcare benchmarks is GPT OSS 20B scored on?

As of September 8, 2026, GPT OSS 20B holds current results on 2 tracked benchmarks: HealthBench Hard, HealthBench.

How does GPT OSS 20B rank on them?

GPT OSS 20B stands at 0.108 on HealthBench Hard (16 of 16 indexed rows), 42.5 on HealthBench (18 of 18 indexed rows).

The benchmarks themselves are described on their pages, linked in the table above, and the whole field is on the index.