Qwen-14BOpen Weight

Released

Qwen-14B is an AI model released by Qwen on Monday, Sep 25 2023, 53 days after Qwen-7B. It is an open-weight model — the trained weights are available to download and run. It is a 14B parameterThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. model with a 2k token context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider.. Benchmark results (shown below) cover HumanEval, MATH, MMLU, and GSM8K.

Benchmarks

Coding

HumanEvalFunction synthesis — 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.
32.3%
#81 of 88

Reasoning & science

MATHReasoning — accuracy on the original competition mathematics test set
24.8%
#51 of 60
MMLUGeneral knowledge — 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.
66.3%
#68 of 81
GSM8KGrade-school math — 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.
61.3%
#46 of 56

Compare Qwen-14B with

Qwen-14B

About

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.

Frequently asked questions

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

All Qwen releases

42 tracked