Mathematics Leaderboard

Mathematics benchmark covering algebra, geometry, number theory, and calculus problems.

Data from LayerLens

As of November 21, 2026, the top-scoring model on Mathematics is Claude Opus 4.6 at 95.6%, followed by Claude Opus 4.6 at 95.6% and GLM 5 at 94.0%. 18 models have been evaluated on this benchmark.

Last updated: November 21, 2026

8 Ways to Use Fewer Tokens

Models

18

Best Score

95.6

Average

83.2

Std Dev

9.3

Categories
Mathematical Problem Solving
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
Mathematics
Actions
$5.000
$25.000
95.6
$5.000
$25.000
95.6
$0.600
$1.920
94.0
$0.600
$1.920
94.0
$0.120
$0.500
93.0
$0.120
$0.500
93.0
$0.200
$0.600
86.8
$0.080
$0.160
84.9
$0.440
$2.200
84.2
$0.014
$0.028
83.1
$0.100
$0.300
80.0
$0.070
$0.140
78.2
$2.500
$10.000
77.2
$0.800
$3.200
74.8
$0.030
$0.050
74.4
$1.000
$10.000
70.8
$0.060
$0.240
70.1
$0.035
$0.140
67.0

Pricing from OpenRouter. Benchmarks from Artificial Analysis.

About Mathematics

Mathematics benchmark covering algebra, geometry, number theory, and calculus problems.

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

Frequently Asked Questions

Mathematics benchmark covering algebra, geometry, number theory, and calculus problems.
As of November 21, 2026, Claude Opus 4.6 leads the Mathematics leaderboard with a score of 95.6. Rankings change as new models are released and evaluated.
Currently 18 models have been evaluated on Mathematics, with an average score of 83.2 and standard deviation of 9.3.
Benchmark scores are updated when new evaluations are published by our data sources (Artificial Analysis and LayerLens). Pricing data is refreshed daily from OpenRouter.