Compare AI models

Specifications
Parameters
47B6B
Context window
32k8k
Benchmarks
HumanEval
40.2%58.5%
HellaSwag
84.4%79.7%
MMLU
70.6%61.4%
GSM8K
58.4%72.3%
Overview
CompanyMistralZ.ai
Release dateDec 8 2023Oct 27 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mixtral 8×7B and ChatGLM3-6B are evenly matched across the 4 benchmarks they both report (HumanEval, HellaSwag, MMLU, GSM8K). ChatGLM3-6B shipped 42 days before Mixtral 8×7B, so benchmark comparisons should account for the intervening progress.

Mixtral 8×7B has 47B parameters, while ChatGLM3-6B has 6B. Context windows are 32k (Mixtral 8×7B) vs 8k (ChatGLM3-6B).

On HumanEval, ChatGLM3-6B leads at 58.5% vs Mixtral 8×7B at 40.2%. On HellaSwag, Mixtral 8×7B leads at 84.4% vs ChatGLM3-6B at 79.7%. On MMLU, Mixtral 8×7B leads at 70.6% vs ChatGLM3-6B at 61.4%. On GSM8K, ChatGLM3-6B leads at 72.3% vs Mixtral 8×7B at 58.4%.