Compare AI models

Specifications
Parameters
8B—
Context window
1M128k
Benchmarks
MATH
35.9%57.9%
MMLU
68.1%81.9%
Overview
CompanyGoogleZ.ai
Release dateOct 3 2024Jun 5 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

GLM-4-Air leads Gemini 1.5 Flash-8B on 2 of the 2 benchmarks they both report (MATH, MMLU). GLM-4-Air shipped 120 days before Gemini 1.5 Flash-8B, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 1.5 Flash-8B) vs 128k (GLM-4-Air).

On MATH, GLM-4-Air leads at 57.9% vs Gemini 1.5 Flash-8B at 35.9%. On MMLU, GLM-4-Air leads at 81.9% vs Gemini 1.5 Flash-8B at 68.1%.