Best AI Models for Math (2026)
Ranked by competition-math benchmarks — AIME 2025 (hard integer-answer problems) and MATH-500. The leaders here are your best bet for quantitative reasoning and step-by-step math.
| # | Model | Math avg | Price / 1M |
|---|---|---|---|
| 1 | Claude Sonnet 4.6 | 95.6% | $6.00 |
| 2 |  Kimi K2 Thinking | 94.5% | $1.07 |
| 3 |  Gemini 2.5 Pro | 88% | $3.44 |
Based on verified public benchmarks; see methodology. Prices are blended 3:1 input:output per million tokens.
More rankings
FAQ
What is the best AI model for math?
Claude Sonnet 4.6 leads this ranking with 95.6%. The full top 20 is in the table above, updated as new benchmark results land.
How is this ranking calculated?
Ranked by competition-math benchmarks — AIME 2025 (hard integer-answer problems) and MATH-500. The leaders here are your best bet for quantitative reasoning and step-by-step math. We only use publicly verifiable benchmark results with cited sources — no estimates. See our methodology page for the exact formula.
How often does this list change?
Pricing and model availability refresh hourly from OpenRouter; benchmark scores update whenever a lab publishes new official results. The ranking reflects the latest verified data.