Compare AI models

Specifications
Context window
32k128k
Benchmarks
HumanEval
67.7%75.7%
MATH
32.6%57.9%
MMLU
71.8%81.9%
GSM8K
77.9%90.9%
Overview
CompanyGoogleZ.ai
Release dateDec 13 2023Jun 5 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

GLM-4-Air leads Gemini 1.0 Pro on 4 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). Gemini 1.0 Pro shipped 175 days before GLM-4-Air, so benchmark comparisons should account for the intervening progress.

Context windows are 32k (Gemini 1.0 Pro) vs 128k (GLM-4-Air).

On HumanEval, GLM-4-Air leads at 75.7% vs Gemini 1.0 Pro at 67.7%. On MATH, GLM-4-Air leads at 57.9% vs Gemini 1.0 Pro at 32.6%. On MMLU, GLM-4-Air leads at 81.9% vs Gemini 1.0 Pro at 71.8%. On GSM8K, GLM-4-Air leads at 90.9% vs Gemini 1.0 Pro at 77.9%.