Mathematics Leaderboard

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

As of March 16, 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 o4 Mini High at 94.6%. 34 models have been evaluated on this benchmark.

Last updated: March 16, 2026

Models

Best Score

95.6

Average

84.2

Std Dev

12.0

Categories

Mathematical Problem Solving

SourceLayerLens

Provider	Model	Input $/M	Output $/M	Mathematics	Actions
A Anthropic	Claude Opus 4.6 Thinking	$5.000	$25.000	95.6	Try
A Anthropic	Claude Opus 4.6	$5.000	$25.000	95.6	Try
O OpenAI	o4 Mini High	$1.100	$4.400	94.6	Try
Z Z AI	GLM 5 Thinking	$0.720	$2.300	94.0	Try
Z Z AI	GLM 5	$0.720	$2.300	94.0	Try
O OpenAI	o3 Mini	$1.100	$4.400	93.1	Try
AL Alibaba	Qwen3 30B A3B Thinking	$0.080	$0.280	93.0	Try
AL Alibaba	Qwen3 30B A3B	$0.080	$0.280	93.0	Try
DS DeepSeek	R1	$0.550	$2.190	92.7	Try
AL Alibaba	QwQ 32B	$0.150	$0.400	92.1	Try
AL Alibaba	QwQ 32B	$0.150	$0.400	92.1	Try
X Xai	Grok 3 Beta	$3.000	$15.000	92.0	Try
A Anthropic	Claude Opus 4 Thinking	$15.000	$75.000	91.2	Try
A Anthropic	Claude Opus 4	$15.000	$75.000	91.2	Try
G Google	Gemini 2.0 Flash	$0.100	$0.400	90.7	Try
A Anthropic	Claude Sonnet 4 Thinking	$3.000	$15.000	90.3	Try
A Anthropic	Claude Sonnet 4	$3.000	$15.000	90.3	Try
A Anthropic	Claude 3.7 Sonnet Thinking	$3.000	$15.000	89.0	Try
A Anthropic	Claude 3.7 Sonnet	$3.000	$15.000	89.0	Try
M Meta	Llama 4 Maverick	$0.150	$0.600	86.8	Try
G Google	Gemma 3 27B	$0.030	$0.110	84.9	Try
MI Mistral	Mistral Medium 3	$0.400	$2.000	84.2	Try
DS Deepseek	DeepSeek V3	$0.014	$0.028	83.1	Try
M Meta	Llama 4 Scout	$0.080	$0.300	80.0	Try
MS Microsoft Azure	Phi 4	$0.060	$0.140	78.2	Try
CO Cohere	Command A	$2.500	$10.000	77.2	Try
AM Amazon	Nova Pro 1.0	$0.800	$3.200	74.8	Try
M Meta	Llama 3.2 3B Instruct	$0.030	$0.050	74.4	Try
A Anthropic	Claude 3.5 Haiku	$0.800	$4.000	73.6	Try
G Google	Gemini 2.5 Pro	$1.000	$10.000	70.8	Try
AM Amazon	Nova Lite 1.0	$0.060	$0.240	70.1	Try
MI Mistral	Pixtral Large 2411	$2.000	$6.000	68.5	Try
AM Amazon	Nova Micro 1.0	$0.035	$0.140	67.0	Try
IF Inflection	Inflection 3 Pi	$2.500	$10.000	36.9	Try

Pricing from OpenRouter. Benchmarks from Artificial Analysis.

108 out of our 483 tracked models have had a price change in March.

Get our weekly newsletter on pricing changes, new releases, and tools.

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.