Best AI models for math
The Math Index aggregates competition and advanced math evaluations (including AIME). These problems require real symbolic reasoning across multiple novel steps, memorization gets a model nowhere.
- 馃
gpt-5.2OpenAI路$1.75 / $14.00 per 1M99.099.0 - 馃
gemini-3-flash-previewGoogle Gemini API路$0.50 / $3.00 per 1M97.097.0 - 馃gemini-3-pro-previewGoogle Gemini API路$2.00 / $12.00 per 1M95.795.7
- 4
GLM-4.7Z.ai路$0.60 / $2.20 per 1M95.095.0 - 5
kimi-k2Google Vertex AI路$0.60 / $2.50 per 1M94.794.7 - 6gpt-5OpenAI路$1.25 / $10.00 per 1M94.394.3
- 7gpt-5.1OpenAI路$1.25 / $10.00 per 1M94.094.0
- 8gpt-oss-120bGroq路$0.15 / $0.75 per 1M93.493.4
- 9grok-4xAI路$3.00 / $15.00 per 1M92.792.7
- 10deepseek-v3.2Google Vertex AI路$0.56 / $1.68 per 1M92.092.0
- 11
claude-opus-4-5Anthropic路$5.00 / $25.00 per 1M91.391.3 - 12nemotron-3-nano-30b-a3bNVIDIA路Free / Free per 1M91.091.0
- 13
Qwen/Qwen3-235B-A22B-Instruct-2507DeepInfra路$0.07 / $0.10 per 1M91.091.0 - 14o4-miniOpenAI路$1.10 / $4.40 per 1M90.790.7
- 15grok-4-fastxAI路$0.20 / $0.50 per 1M89.789.7
- 16o3OpenAI路$2.00 / $8.00 per 1M88.388.3
- 17claude-sonnet-4-5Anthropic路$3.00 / $15.00 per 1M88.088.0
- 18gemini-2.5-proGoogle Gemini API路$1.25 / $10.00 per 1M87.787.7
- 19GLM-4.6Z.ai路$0.60 / $2.20 per 1M86.086.0
- 20gpt-5-miniOpenAI路$0.25 / $2.00 per 1M85.085.0
- 21grok-3-minixAI路$0.30 / $0.50 per 1M84.784.7
- 22claude-haiku-4-5Anthropic路$1.00 / $5.00 per 1M83.783.7
- 23gpt-5-nanoOpenAI路$0.05 / $0.40 per 1M83.783.7
- 24Qwen/Qwen3-235B-A22BDeepInfra路$0.20 / $0.60 per 1M82.082.0
- 25zai-org/GLM-4.5-AirDeepInfra路$0.20 / $1.10 per 1M80.780.7
- 26claude-opus-4-1Google Vertex AI路$15.00 / $75.00 per 1M80.380.3
- 27minimax-m2MiniMax路$0.30 / $1.20 per 1M78.378.3
- 28
deepseek-r1Novita AI路$4.00 / $4.00 per 1M76.076.0 - 29claude-sonnet-4Google Vertex AI路$3.00 / $15.00 per 1M74.374.3
- 30gemini-2.5-flashGoogle Gemini API路$0.30 / $2.50 per 1M73.373.3
Explore other rankings
Smartest overall
Ranked by Intelligence Index
Best for coding
Ranked by Coding Index
Best coding agent
Ranked by Terminal-Bench Hard
Best for reasoning
Ranked by GPQA Diamond
Best for tool use
Ranked by 蟿虏-Bench
Best for knowledge
Ranked by MMLU Pro
Cheapest
Lowest input + output price per 1M tokens
Longest context
Max tokens in a single prompt
How we rank
Scores for Math Index come from Artificial Analysis, an independent AI benchmarking service. When a model is available through multiple providers (e.g. Anthropic direct, AWS Bedrock, Google Vertex), we show one canonical entry per model family so the ranking isn't polluted by duplicates. Benchmarks measure specific skills, so always validate on your own workload before committing.
One API for every model on this list
Requesty is OpenAI-compatible and routes to 600+ models. Switch between any of the models above by changing one parameter in your code.