Best AI Models for Math
Ranking of language models by mathematical reasoning. These models excel at solving complex math problems from algebra to competition-level.Updated August 2026. Based on independent benchmark data.
Why This Matters
Choosing the right model for math is about more than raw benchmark scores. The models below are ranked using a weighted blend of category-specific benchmarks, arena Elo, and the intelligence index — but real-world performance depends on your context window, latency budget, and integration path.
For math, we weighted the benchmarks that most strongly predict success in production: task accuracy first, then speed and cost efficiency. Leaders on this page consistently outperform on both standardized tests and real-world workloads.
If you operate under a strict budget, check the Best Value LLMs ranking. If latency matters more than raw quality, see Fastest LLMs. Both pages use the same underlying dataset with different weightings.
| # | Model | Provider | Score | Speed | Price (output) |
|---|---|---|---|---|---|
| 1 | Claude Mythos Preview | Anthropic | 100.0 | 80 t/s | $15/M |
| 2 | MiMo V2.5 Pro | Xiaomi | 100.0 | 65 t/s | $0.87/M |
| 3 | GPT-6 Astra | OpenAI | 97.6 | 82 t/s | $50/M |
| 4 | MiMo V2.6 Pro | Xiaomi | 95.0 | 72 t/s | $0.95/M |
| 5 | Claude Fable 5.1 | Anthropic | 92.0 | 85 t/s | $15/M |
| 6 | GPT-6 Astra (xhigh) | OpenAI | 90.0 | 76 t/s | $50/M |
| 7 | GPT-6 Astra (high) | OpenAI | 90.0 | 90 t/s | $50/M |
| 8 | GPT-6 Astra (medium) | OpenAI | 90.0 | 98 t/s | $50/M |
| 9 | GPT-6 Astra (low) | OpenAI | 90.0 | 110 t/s | $50/M |
| 10 | Muse Spark 1.3 | Muse | 90.0 | 75 t/s | $10/M |
| 11 | GPT-6 Luna | OpenAI | 88.0 | 120 t/s | $20/M |
| 12 | Claude Opus 5.5 | Anthropic | 86.0 | 68 t/s | $25/M |
| 13 | Claude Fable 5.1 (XHigh) | Anthropic | 85.0 | 78 t/s | $15/M |
| 14 | Claude Fable 5.1 (High) | Anthropic | 85.0 | 92 t/s | $15/M |
| 15 | Claude Fable 5.1 (Medium) | Anthropic | 85.0 | 104 t/s | $15/M |
| 16 | Claude Fable 5.1 (Low) | Anthropic | 85.0 | 118 t/s | $15/M |
| 17 | Grok 4 Heavy | xAI | 84.6 | 50 t/s | $15/M |
| 18 | Claude Opus 5 | Anthropic | 82.3 | 60 t/s | $25/M |
| 19 | Qwen3.7 Max | Alibaba | 81.6 | 203 t/s | $7.5/M |
| 20 | Claude Fable 5 | Anthropic | 81.0 | 71 t/s | $50/M |
Top 5 Math — Quick Comparison
Methodology
Rankings are based on independent benchmark evaluations. The math score is computed from multiple standardized benchmarks and normalized to 0–100. Data is updated regularly from public benchmark results.
Related Rankings
Frequently Asked Questions
What is the best AI model for math problem solving?
Reasoning models like OpenAI o3, DeepSeek-R1, and Claude 3.7 Sonnet achieve top scores on MATH-500 and competition mathematics.