MedQA Leaderboard

Medical question answering benchmark from USMLE-style questions.

Data from LayerLens

As of November 21, 2026, the top-scoring model on MedQA is Gemini 2.5 Pro at 94.6%, followed by R1 at 92.1% and GPT-4.1 at 89.7%. 19 models have been evaluated on this benchmark.

Last updated: November 21, 2026

8 Ways to Use Fewer Tokens

Models

19

Best Score

94.6

Average

77.6

Std Dev

11.2

Categories
Reasoning and Logic
Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
MedQA
Actions
$1.000
$10.000
94.6
$0.550
$2.190
92.1
$2.000
$8.000
89.7
$0.780
$3.900
85.5
$0.120
$0.500
85.3
$0.120
$0.500
85.3
$0.000
$0.000
84.8
$0.014
$0.028
80.3
$0.800
$3.200
79.3
$0.440
$2.200
79.1
$0.200
$0.600
78.4
$0.070
$0.140
77.8
$2.500
$10.000
73.3
$1.000
$3.000
72.8
$1.000
$3.000
72.8
$0.075
$0.200
70.5
$0.080
$0.160
67.5
$0.030
$0.050
52.6
$0.100
$0.300
52.0

Pricing from OpenRouter. Benchmarks from Artificial Analysis.

About MedQA

Medical question answering benchmark from USMLE-style questions.

This leaderboard shows all models with MedQA benchmark scores, ranked from highest to lowest. Pricing data is included to help you compare performance against cost.

Frequently Asked Questions

Medical question answering benchmark from USMLE-style questions.
As of November 21, 2026, Gemini 2.5 Pro leads the MedQA leaderboard with a score of 94.6. Rankings change as new models are released and evaluated.
Currently 19 models have been evaluated on MedQA, with an average score of 77.6 and standard deviation of 11.2.
Benchmark scores are updated when new evaluations are published by our data sources (Artificial Analysis and LayerLens). Pricing data is refreshed daily from OpenRouter.