ChatGLM3-6BOpen Weight

Released

ChatGLM3-6B is an AI model released by Z.ai on Friday, Oct 27 2023, 94 days after CodeGeeX2-6B. It is an open-weight model — the trained weights are available to download and run. It is a 6B 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 8k 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.
58.5%
#57 of 74

Reasoning & science

MATHReasoning — accuracy on the original competition mathematics test set
25.7%
#41 of 50
HellaSwagReasoning — commonsense completion of short scenarios
79.7%
#15 of 17
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.
61.4%
#62 of 68
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.
72.3%
#28 of 39

Compare ChatGLM3-6B with

ChatGLM3-6B

About

ChatGLM3-6B was released in October 2023 as the third generation of the bilingual ChatGLM family. Its dialogue format supported function calls and code interpreter workflows, expanding the types of applications developers could build around the chat model.

The launch included base, dialogue and long-context weights. The standard 6B dialogue model used an 8K context, and the 32K checkpoint served longer inputs. The GLM family's cross-generation benchmark table reports results for the 6B base checkpoint.

Frequently asked questions

ChatGLM3-6B was released by Z.ai on Friday, Oct 27 2023.

All Z.ai releases

24 tracked