86Fit score
Aion-1.0-Mini 32B parameter model is a distilled version of the DeepSeek-R1 model, designed for strong performance in reasoning domains such as mathematics, coding, and logic. It is a modified variant of a FuseAI model t…
Model details →Best AI models for math
Math performance correlates strongly with overall reasoning. The leaders here are also the leaders on GPQA and MMLU.
86Fit score
Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and ext…
Model details →86Fit score
Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and ext…
Model details →Top 25 models for math problems
| # | Model | Provider | Context | Input price / 1M | Tier |
|---|---|---|---|---|---|
| 1 | AionLabs: Aion-1.0-Mini | Aion Labs | 131K Long context (128K+) | $0.70 | Budget |
| 2 | Anthropic: Claude 3.7 Sonnet | Anthropic | 200K Long context (128K+) | $3.00 | Standard |
| 3 | Anthropic: Claude 3.7 Sonnet (thinking) | Anthropic | 200K Long context (128K+) | $3.00 | Standard |
| 4 | Baidu: ERNIE 4.5 21B A3B Thinking | Baidu | 131K Long context (128K+) | $0.07 | Budget |
| 5 | DeepSeek: R1 Distill Qwen 32B | DeepSeek | 33K Short/standard context | $0.29 | Budget |
| 6 | Google: Gemini 2.5 Flash | 1.0M Ultra context (1M+) | $0.30 | Budget | |
| 7 | Google: Gemini 2.5 Flash (batch) | 1.0M Ultra context (1M+) | $0.15 | Budget | |
| 8 | Google: Gemini 2.5 Pro | 1.0M Ultra context (1M+) | $1.25 | Standard | |
| 9 | Google: Gemini 2.5 Pro (batch) | 1.0M Ultra context (1M+) | $0.63 | Budget | |
| 10 | Google: Gemini 2.5 Pro Preview 05-06 | 1.0M Ultra context (1M+) | $1.25 | Standard | |
| 11 | Google: Gemini 2.5 Pro Preview 06-05 | 1.0M Ultra context (1M+) | $1.25 | Standard | |
| 12 | Google: Gemini 3 Pro Preview | 1.0M Ultra context (1M+) | $2.00 | Standard | |
| 13 | Qwen: Qwen3 8B | Qwen | 131K Long context (128K+) | $0.12 | Budget |
| 14 | IBM: Granite 4.2 8B | Ibm Granite | 131K Long context (128K+) | $0.06 | Budget |
| 15 | NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 | Nvidia | 131K Long context (128K+) | $0.10 | Budget |
| 16 | NVIDIA: Nemotron Nano 12B 2 VL | Nvidia | 131K Long context (128K+) | $0.20 | Budget |
| 17 | OpenAI: o3 | OpenAI | 200K Long context (128K+) | $2.00 | Standard |
| 18 | OpenAI: o3 (batch) | OpenAI | 200K Long context (128K+) | $1.00 | Standard |
| 19 | OpenAI: o3 Mini | OpenAI | 200K Long context (128K+) | $1.10 | Standard |
| 20 | OpenAI: o3 Mini (batch) | OpenAI | 200K Long context (128K+) | $0.55 | Budget |
| 21 | OpenAI: o3 Mini High | OpenAI | 200K Long context (128K+) | $1.10 | Standard |
| 22 | OpenAI: o3 Mini High (batch) | OpenAI | 200K Long context (128K+) | $0.55 | Budget |
| 23 | Prime Intellect: INTELLECT-3 | Prime Intellect | 131K Long context (128K+) | $0.20 | Budget |
| 24 | PrismML: Ternary Bonsai 2 27B | Prism Ml | 262K Long context (128K+) | $0.07 | Budget |
| 25 | Qwen: Qwen3 235B A22B | Qwen | 131K Long context (128K+) | $0.46 | Budget |
Frequently asked questions
What's the best model for math homework help?
Reasoning models (o-series, Claude thinking, DeepSeek R1) lead. For free options, DeepSeek R1 distilled variants run locally.
Related use cases
AI models for codingAI reasoning modelsAI vision modelslong-context AI models (128K+)AI models for function callingAI models for structured / JSON outputsAI models for agentsfree AI modelsCheapest AI models per tokenmultilingual AI modelsembedding modelssmall / on-device AI modelsAI image generation modelsAI voice / audio modelsAI models for writingopen-source AI modelsAI models for RAGAI models for summarizationAI models for translationAI models for enterprise