Health Evals

xAI logoGrok 4.20: healthcare benchmark results

xAI · 2 boards · snapshot reviewed September 28, 2026

The index currently holds 2 results for Grok 4.20: 65.8% on MedXpertQA (MM) (13 of 22 indexed rows), 5.3 ± 3.2 on PhysicianBench [Grok-4.20] (21 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
MedXpertQA (MM)
Meta's Muse Spark launch table (Meta reports the better of vendor self-reports and its own reproduction)
65.8%13 of 222026-04
PhysicianBench
Grok-4.20
5.3 ± 3.221 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 "Grok-4.20".

Which healthcare benchmarks is Grok 4.20 scored on?

As of September 28, 2026, Grok 4.20 has indexed results on 2 tracked benchmarks: MedXpertQA (MM), PhysicianBench.

Which results are indexed for Grok 4.20?

Grok 4.20 stands at 65.8% on MedXpertQA (MM) (13 of 22 indexed rows), 5.3 ± 3.2 on PhysicianBench [Grok-4.20] (21 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.