Compare AI models

Specifications
Parameters
141B6B
Context window
64k32k
API pricing
Cheapest input
$2.00Mistral—
Cheapest output
$6.00Mistral—
$700Mistral · zdr—
Benchmarks
HumanEval
45.1%9.8%
HellaSwag
88.5%57%
MMLU
77.75%45.2%
GSM8K
78.6%25.9%
Overview
CompanyMistralZ.ai
Release dateApr 10 2024Jun 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mixtral 8×22B leads ChatGLM2-6B on 4 of the 4 benchmarks they both report (HumanEval, HellaSwag, MMLU, GSM8K). ChatGLM2-6B shipped 290 days before Mixtral 8×22B, so benchmark comparisons should account for the intervening progress.

Mixtral 8×22B has 141B parameters, while ChatGLM2-6B has 6B. Context windows are 64k (Mixtral 8×22B) vs 32k (ChatGLM2-6B).

On HumanEval, Mixtral 8×22B leads at 45.1% vs ChatGLM2-6B at 9.8%. On HellaSwag, Mixtral 8×22B leads at 88.5% vs ChatGLM2-6B at 57%. On MMLU, Mixtral 8×22B leads at 77.75% vs ChatGLM2-6B at 45.2%. On GSM8K, Mixtral 8×22B leads at 78.6% vs ChatGLM2-6B at 25.9%.