Gemini 2.5 Pro: healthcare benchmark results
Google · 6 boards · snapshot reviewed September 28, 2026
The index currently holds 6 results for Gemini 2.5 Pro: 0.529 on MedHELM (6 of 10 indexed rows), 61.9% on First, Do NOHARM (v2) (13 of 17 indexed rows), 50.59% on MedCode (Vals AI) (15 of 102 indexed rows), 73.55% on MedScribe (Vals AI) (79 of 104 indexed rows), 0.31 on EHR-Complex (16 of 18 indexed rows), 35.3% on WHBench (21 of 22 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
| benchmark | score | index position | as of |
|---|---|---|---|
| MedHELM | 0.529 | 6 of 10 source board: 11 | 2026-05 |
| First, Do NOHARM (v2) | 61.9% | 13 of 17 source board: 19 | 2026-08 |
| MedCode (Vals AI) model ID google/gemini-2.5-pro; temperature=1; max_output_tokens=30000; standard error 2.113 pp; $0.015389/test; source snapshot 2026-09-26; run date not published | 50.59% | 15 of 102 | 2026-09-26 |
| MedScribe (Vals AI) model ID google/gemini-2.5-pro; temperature=1; max_output_tokens=30000; standard error 1.91 pp; $0.046379/test; source snapshot 2026-09-26; run date not published | 73.55% | 79 of 104 | 2026-09-26 |
| EHR-Complex Table 3; macro-average across 12 intent/scope columns; temperature 0; up to 50 SQL/Python interaction turns via paper, arxiv.org | 0.31 | 16 of 18 | 2026-06 |
| WHBench 95% bootstrap CI 32.7–38.1; 3 runs; temperature 0; zero-shot, closed-book via paper, arxiv.org | 35.3% | 21 of 22 | 2026-03 |
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.
Which healthcare benchmarks is Gemini 2.5 Pro scored on?
As of September 28, 2026, Gemini 2.5 Pro has indexed results on 6 tracked benchmarks: MedHELM, First, Do NOHARM (v2), MedCode (Vals AI), MedScribe (Vals AI), EHR-Complex, WHBench.
Which results are indexed for Gemini 2.5 Pro?
Gemini 2.5 Pro stands at 0.529 on MedHELM (6 of 10 indexed rows), 61.9% on First, Do NOHARM (v2) (13 of 17 indexed rows), 50.59% on MedCode (Vals AI) (15 of 102 indexed rows), 73.55% on MedScribe (Vals AI) (79 of 104 indexed rows), 0.31 on EHR-Complex (16 of 18 indexed rows), 35.3% on WHBench (21 of 22 indexed rows).
The benchmarks themselves are described on their pages, linked in the table above, and the whole field is on the index.