Compare AI models

Specifications
Context window
100k—
Benchmarks
HumanEval
71.2%72%
MMLU
78.5%81.5%
GSM8K
88%87.6%
Overview
CompanyAnthropicZ.ai
Release dateJul 11 2023Jan 16 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

GLM-4 leads Claude 2 on 2 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Claude 2 shipped 189 days before GLM-4, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On HumanEval, GLM-4 leads at 72% vs Claude 2 at 71.2%. On MMLU, GLM-4 leads at 81.5% vs Claude 2 at 78.5%. On GSM8K, Claude 2 leads at 88% vs GLM-4 at 87.6%.