Best AI models for math

AI models ranked on math benchmarks: MATH, AIME, and advanced arithmetic reasoning.

Math-capable models solve competition-style problems and symbolic derivations reliably.

  1. 1

    Phi-4

    86.5Frontier
    Microsoft
    Context:
    16K
    MathFrontierOpen source
  2. 2

    DeepSeek V3

    84.0Frontier
    DeepSeek
    Context:
    128K
    Input:
    $0.27/1M
    Output:
    $1.1/1M
    MathAgenticFrontierOpen sourceCode
  3. 3

    o3

    83.5Frontier
    OpenAI
    Context:
    200K
    Input:
    $2/1M
    Output:
    $8/1M
    VisionMathAgenticLong contextFrontierReasoning
  4. 4

    Gemini 2 Pro

    82.8Frontier
    Google
    Context:
    2M
    Input:
    $1.25/1M
    Output:
    $5/1M
    VisionMathAgenticLong contextFrontierCode
  5. 5

    Grok 3

    80.1Frontier
    xAI
    Context:
    131K
    Input:
    $3/1M
    Output:
    $15/1M
    VisionMathAgenticFrontierReasoning
  6. 6

    GPT-5

    77.9Strong
    OpenAI
    Context:
    272K
    Input:
    $1.25/1M
    Output:
    $10/1M
    VisionMathAgenticLong contextReasoningCode
  7. 7

    GPT-4o mini

    77.1Strong
    OpenAI
    Context:
    128K
    Input:
    $0.15/1M
    Output:
    $0.6/1M
    VisionMathAgenticBudget
  8. 8

    DeepSeek R1

    76.9Strong
    DeepSeek
    Context:
    128K
    Input:
    $0.55/1M
    Output:
    $2.19/1M
    MathOpen sourceReasoning
  9. 9

    o1

    76.3Strong
    OpenAI
    Context:
    200K
    Input:
    $15/1M
    Output:
    $60/1M
    VisionMathAgenticLong contextReasoning
  10. 10

    o3-mini

    74.5Strong
    OpenAI
    Context:
    200K
    Input:
    $1.1/1M
    Output:
    $4.4/1M
    MathAgenticLong contextCode