Compare AI models

Specifications
Context window
128k128k
Benchmarks
HumanEval
83.7%75.7%
MATH
64.3%57.9%
MMLU
84.7%81.9%
Overview
CompanyOpenAIZ.ai
Release dateNov 6 2023Jun 5 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

GPT-4 Turbo leads GLM-4-Air on 3 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). GPT-4 Turbo shipped 212 days before GLM-4-Air, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (GPT-4 Turbo) vs 128k (GLM-4-Air).

On HumanEval, GPT-4 Turbo leads at 83.7% vs GLM-4-Air at 75.7%. On MATH, GPT-4 Turbo leads at 64.3% vs GLM-4-Air at 57.9%. On MMLU, GPT-4 Turbo leads at 84.7% vs GLM-4-Air at 81.9%.