Compare AI models

Specifications
Context window
128k—
Benchmarks
HumanEval
83.7%72%
MATH
64.3%47.9%
MMLU
84.7%81.5%
Overview
CompanyOpenAIZ.ai
Release dateNov 6 2023Jan 16 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

GPT-4 Turbo leads GLM-4 on 3 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). GPT-4 Turbo shipped 71 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, GPT-4 Turbo leads at 83.7% vs GLM-4 at 72%. On MATH, GPT-4 Turbo leads at 64.3% vs GLM-4 at 47.9%. On MMLU, GPT-4 Turbo leads at 84.7% vs GLM-4 at 81.5%.