# Qwen-14B

Qwen-14B is an AI model released by Qwen on Sep 25 2023. It has 14B parameters, a 2k context window and open weight.

## Facts

| Field | Value |
| --- | --- |
| Model | Qwen-14B |
| Developer | Qwen |
| Release date | Monday, Sep 25 2023 |
| Licensing | Open Weight |
| Parameters | 14B |
| Context window | 2k |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| HumanEval | 32.3% | Lab | 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. |
| MATH | 24.8% | Lab | accuracy on the original competition mathematics test set |
| MMLU | 66.3% | Lab | A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. |
| GSM8K | 61.3% | 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 Qwen-14B

Qwen-14B expanded Alibaba Cloud's first Qwen generation on September 25, 2023. Alibaba released base and chat weights for the new model alongside an update to Qwen-7B and the first release of Qwen-Agent.

The 14B base model scored 66.3 on MMLU and 32.3 on HumanEval in Qwen's published evaluation, compared with 56.7 and 24.4 for the original 7B base model. It gave developers an intermediate size before the 72B model arrived that November.

## Questions and answers

### When was Qwen-14B released?

Qwen-14B was released by Qwen on Monday, Sep 25 2023.

### Who made Qwen-14B?

Qwen-14B 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 Qwen-14B get?

Qwen-14B reports 4 tracked benchmark scores — HumanEval: 32.3%; MATH: 24.8%; MMLU: 66.3%; GSM8K: 61.3%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

### What is the context window of Qwen-14B?

Qwen-14B has a context window of 2k. Providers may specify separate input and output token limits.

### How many parameters does Qwen-14B have?

Qwen-14B is reported at 14B parameters.

### Is Qwen-14B open source?

Partly. Qwen-14B 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 Qwen-14B?

Qwen's previous tracked release was Qwen-7B on Aug 3 2023, 53 days earlier. It was followed by Qwen-72B on Nov 30 2023.


---

Canonical page: https://aireleasetracker.com/model/qwen/qwen-14b
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.
