Clinical Benchmarks

Google logoGemini 3.1 Pro: healthcare benchmark results

Google · 6 boards · updated August 16, 2026

The index currently holds 6 results for Gemini 3.1 Pro: 58.9% on MAST (Medical AI Superintelligence Test) (4 of 11), 62.6% on First, Do NOHARM (v2) (5 of 19), 81.3% on MedXpertQA (MM) (1 of 8), 6.0 ± 1.0 on PhysicianBench (8 of 13), 0.63 on EHR-Complex (2 of 12), 11.9% on HealthAdminBench (5 of 5). It tops MedXpertQA (MM). 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

benchmarkscorepositionas of
MAST (Medical AI Superintelligence Test)
via ARISE MAST leaderboard
58.9%4 of 112026-08
First, Do NOHARM (v2)
via ARISE MAST technical leaderboard
62.6%5 of 192026-08
MedXpertQA (MM)
via benchlm.ai mirror of Meta's Muse Spark evaluation
81.3%1 of 82026-08
PhysicianBench
via PhysicianBench paper (Table 2)
6.0 ± 1.08 of 132026-05
EHR-Complex
via EHR-Complex paper
0.632 of 122026-06
HealthAdminBench
via Kinetic Systems blog
11.9%5 of 52026-04

Position counts against the source's full board, including rows this index does not mirror. Config caveats, where a source noted any, are on each benchmark's page. Sources also list this model as "Gemini Pro 3.1".

Which healthcare benchmarks is Gemini 3.1 Pro scored on?

As of August 16, 2026, Gemini 3.1 Pro holds current results on 6 tracked benchmarks: MAST (Medical AI Superintelligence Test), First, Do NOHARM (v2), MedXpertQA (MM), PhysicianBench, EHR-Complex, HealthAdminBench.

How does Gemini 3.1 Pro rank on them?

Gemini 3.1 Pro stands at 58.9% on MAST (Medical AI Superintelligence Test) (4 of 11), 62.6% on First, Do NOHARM (v2) (5 of 19), 81.3% on MedXpertQA (MM) (1 of 8), 6.0 ± 1.0 on PhysicianBench (8 of 13), 0.63 on EHR-Complex (2 of 12), 11.9% on HealthAdminBench (5 of 5). It holds first place on MedXpertQA (MM).

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