Qwen1.5-110BOpen Weight

Released

Qwen1.5-110B is an AI model released by Qwen on Thursday, Apr 25 2024, 9 days after CodeQwen1.5. It is an open-weight model — the trained weights are available to download and run. It is a 110B 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 32k 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, HellaSwag, 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.
52.4%
#68 of 88

Reasoning & science

MATHReasoning — accuracy on the original competition mathematics test set
49.6%
#40 of 60
HellaSwagReasoning — commonsense completion of short scenarios
87.5%
#7 of 22
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.
80.4%
#42 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.
85.4%
#29 of 56

Compare Qwen1.5-110B with

Qwen1.5-110B

About

Qwen1.5-110B shipped on April 25, 2024 as the first Qwen1.5 model above 100 billion parameters. The release supplied downloadable base and chat checkpoints and extended the dense lineup beyond the original 72B release.

Qwen reported MMLU 80.4 and GSM8K 85.4 for the base checkpoint. The 110B model represented Alibaba's large dense approach just before Qwen2 offered a stronger 72B model and a separate sparse model in the same launch family.

Frequently asked questions

Qwen1.5-110B was released by Qwen on Thursday, Apr 25 2024.

All Qwen releases

42 tracked