Best AI Models for Math
Top-performing models for mathematics and quantitative tasks, ranked by math benchmark scores.
Based on 5 AI models
Recommended Models
| Ranking | Model | Provider | Math | Benchmark Evidence | Price (in) | Context |
|---|---|---|---|---|---|---|
| 1 | Claude 3.5 Sonnet ビジョン, 推論, コーディング, ツール呼び出し, ロングコンテキスト | Anthropic | 88.7 | 80 | $3.00 | 200,000 |
| 2 | GPT-4o ビジョン, 推論, コーディング, オーディオ, ツール呼び出し | OpenAI | 88.7 | 75.4 | $2.50 | 128,000 |
| 3 | Llama 3.1 405B | Meta | 88.6 | 76.2 | $3.00 | 128,000 |
| 4 | DeepSeek V3 | DeepSeek | 88.5 | 85.6 | $0.27 | 65,536 |
| 5 | Claude 3 Opus | Anthropic | 86.8 | 74 | $15.00 | 200,000 |
Frequently Asked Questions
What is the best model for Math?
Based on our data, Claude 3.5 Sonnet ranks first for Math with a score of 89.
How were these models selected?
Models are ranked by scenario-specific data: benchmark scores (coding/reasoning/math/vision), capability support, context window, or price. All data comes from our transparent model catalog, updated daily.
How fresh is this data?
Model data, prices, and rankings are refreshed on a regular schedule; ranking scores are snapshotted daily. Each model page shows its last verified date.