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
Models
18
Best Score
95.6
Average
83.2
Std Dev
9.3
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.
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.
Built by @aellman
Also from the founder: BlobCap, a price index for AI training data deals, showing what AI labs actually pay for data.
2026 68 Ventures, LLC. All rights reserved.