WMDP Leaderboard

Weapons of Mass Destruction Proxy — benchmark testing knowledge safety boundaries.

Data from LayerLens

As of November 21, 2026, the top-scoring model on WMDP is Gemini 3 Flash Preview at 86.8%, followed by Gemini 3 Flash Preview at 86.8% and DeepSeek V3 at 71.8%. 8 models have been evaluated on this benchmark.

Last updated: November 21, 2026

8 Ways to Use Fewer Tokens

Models

8

Best Score

86.8

Average

64.8

Std Dev

23.7

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
WMDP
Actions
$0.500
$3.000
86.8
$0.500
$3.000
86.8
$0.014
$0.028
71.8
$2.000
$8.000
71.4
$2.500
$10.000
69.6
$0.800
$3.200
67.0
$0.070
$0.140
58.0
$0.030
$0.050
6.7

Pricing from OpenRouter. Benchmarks from Artificial Analysis.

About WMDP

Weapons of Mass Destruction Proxy — benchmark testing knowledge safety boundaries.

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

Frequently Asked Questions

Weapons of Mass Destruction Proxy — benchmark testing knowledge safety boundaries.
As of November 21, 2026, Gemini 3 Flash Preview leads the WMDP leaderboard with a score of 86.8. Rankings change as new models are released and evaluated.
Currently 8 models have been evaluated on WMDP, with an average score of 64.8 and standard deviation of 23.7.
Benchmark scores are updated when new evaluations are published by our data sources (Artificial Analysis and LayerLens). Pricing data is refreshed daily from OpenRouter.