# Qwen2.5-Math

Qwen2.5-Math is an AI model released by Qwen on Sep 19 2024. It has 1.5B/7B/72B parameters, a 4k context window and open weight.

## Facts

| Field | Value |
| --- | --- |
| Model | Qwen2.5-Math |
| Developer | Qwen |
| Release date | Thursday, Sep 19 2024 |
| Licensing | Open Weight |
| Parameters | 1.5B/7B/72B |
| Context window | 4k |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| MATH | 85.9% | Lab | accuracy on the original competition mathematics test set |
| GSM8K | 95.9% | Lab | Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. |

## About Qwen2.5-Math

Qwen2.5-Math arrived on September 19, 2024 with downloadable 1.5B, 7B and 72B checkpoints. It expanded the earlier specialist family with bilingual mathematical reasoning and optional use of a Python interpreter during problem-solving.

In Qwen's technical report, the 72B instruction checkpoint scored 85.9 on MATH with a single chain-of-thought answer. The team also published separate results for tool-integrated reasoning, majority voting and reward-model selection.

## Questions and answers

### When was Qwen2.5-Math released?

Qwen2.5-Math was released by Qwen on Thursday, Sep 19 2024.

### Who made Qwen2.5-Math?

Qwen2.5-Math was built by Qwen. Alibaba's AI lab, building the Qwen family. The most prolific publisher of open-weight models of any major lab, alongside a closed Max and Plus tier sold through Alibaba Cloud.

### What benchmark scores did Qwen2.5-Math get?

Qwen2.5-Math reports 2 tracked benchmark scores — MATH: 85.9%; GSM8K: 95.9%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

### What is the context window of Qwen2.5-Math?

Qwen2.5-Math has a context window of 4k. Providers may specify separate input and output token limits.

### How many parameters does Qwen2.5-Math have?

Qwen2.5-Math is reported at 1.5B/7B/72B parameters.

### Is Qwen2.5-Math open source?

Partly. Qwen2.5-Math is an open-weight model: the trained weights are free to download and run locally or on your own infrastructure, but the training data and code are not fully released and the license may restrict some commercial uses. It is not open source in the strict sense.

### What came before and after Qwen2.5-Math?

Qwen's previous tracked release was Qwen2.5-Coder on Sep 19 2024. It was followed by Qwen2.5-Turbo (1M) on Nov 15 2024.


---

Canonical page: https://aireleasetracker.com/model/qwen/qwen2.5-math
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.
