Compare AI models

Specifications
Context window
1M128k
Benchmarks
HumanEval
71.9%75.7%
MATH
58.5%57.9%
MMLU
81.9%81.9%
GSM8K
91.7%90.9%
Overview
CompanyGoogleZ.ai
Release dateFeb 15 2024Jun 5 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Gemini 1.5 Pro leads GLM-4-Air on 2 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). Gemini 1.5 Pro shipped 111 days before GLM-4-Air, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 1.5 Pro) vs 128k (GLM-4-Air).

On HumanEval, GLM-4-Air leads at 75.7% vs Gemini 1.5 Pro at 71.9%. On MATH, Gemini 1.5 Pro leads at 58.5% vs GLM-4-Air at 57.9%. On MMLU, both models score 81.9%. On GSM8K, Gemini 1.5 Pro leads at 91.7% vs GLM-4-Air at 90.9%.