Health Evals

OpenAI logoGPT-5.5: healthcare benchmark results

OpenAI · 7 boards · snapshot reviewed September 28, 2026

The index currently holds 7 results for GPT-5.5: 0.518 on HealthBench Professional (20 of 29 indexed rows), 0.315 on HealthBench Hard (10 of 20 indexed rows), 56.5 on HealthBench (16 of 26 indexed rows), 70.0% on First, Do NOHARM (v2) (9 of 17 indexed rows), 49.10% on MedCode (Vals AI) [GPT 5.5] (23 of 102 indexed rows), 86.87% on MedScribe (Vals AI) [GPT 5.5] (17 of 104 indexed rows), 46.3 ± 1.2 on PhysicianBench (7 of 21 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 Professional
length-adjusted, max reasoning effort, GPT-5.6 system card Table 6 column GPT-5.5 (57.2 unadjusted, 3818 chars)
0.51820 of 292026-06
HealthBench Hard
length-adjusted, max reasoning effort, GPT-5.6 system card Table 6 column GPT-5.5 (33.8 unadjusted, 2289 chars)
0.31510 of 202026-06
HealthBench
length-adjusted (58.4 unadjusted), comparison row in GPT-5.6 system card
56.516 of 262026-04
First, Do NOHARM (v2)70.0%9 of 17
source board: 19
2026-08
MedCode (Vals AI)
GPT 5.5
model ID openai/gpt-5.5; reasoning_effort=xhigh; temperature=1; max_output_tokens=30000; standard error 2.188 pp; $0.160759/test; source snapshot 2026-09-26; run date not published
49.10%23 of 1022026-09-26
MedScribe (Vals AI)
GPT 5.5
model ID openai/gpt-5.5; reasoning_effort=xhigh; temperature=1; max_output_tokens=30000; standard error 1.932 pp; $0.142988/test; source snapshot 2026-09-26; run date not published
86.87%17 of 1042026-09-26
PhysicianBench
pass@1; Pass^3 28.0
46.3 ± 1.27 of 212026-05

Position follows the rows held in this index and is not a controlled comparison. Sources may use different graders or task subsets. Positions include 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. Sources also list this model as "GPT 5.5".

Which healthcare benchmarks is GPT-5.5 scored on?

As of September 28, 2026, GPT-5.5 has indexed results on 7 tracked benchmarks: HealthBench Professional, HealthBench Hard, HealthBench, First, Do NOHARM (v2), MedCode (Vals AI), MedScribe (Vals AI), PhysicianBench.

Which results are indexed for GPT-5.5?

GPT-5.5 stands at 0.518 on HealthBench Professional (20 of 29 indexed rows), 0.315 on HealthBench Hard (10 of 20 indexed rows), 56.5 on HealthBench (16 of 26 indexed rows), 70.0% on First, Do NOHARM (v2) (9 of 17 indexed rows), 49.10% on MedCode (Vals AI) [GPT 5.5] (23 of 102 indexed rows), 86.87% on MedScribe (Vals AI) [GPT 5.5] (17 of 104 indexed rows), 46.3 ± 1.2 on PhysicianBench (7 of 21 indexed rows).

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