Compare AI models

Specifications
Parameters
8B—
Context window
8k128k
Benchmarks
HumanEval
36.22%75.7%
MMLU
69.51%81.9%
GSM8K
58.45%90.9%
Overview
CompanyNVIDIAZ.ai
Release dateAug 21 2024Jun 5 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

GLM-4-Air leads Mistral NeMo Minitron 8B on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). GLM-4-Air shipped 77 days before Mistral NeMo Minitron 8B, so benchmark comparisons should account for the intervening progress.

Context windows are 8k (Mistral NeMo Minitron 8B) vs 128k (GLM-4-Air). Mistral NeMo Minitron 8B is open weight, while GLM-4-Air is closed.

On HumanEval, GLM-4-Air leads at 75.7% vs Mistral NeMo Minitron 8B at 36.22%. On MMLU, GLM-4-Air leads at 81.9% vs Mistral NeMo Minitron 8B at 69.51%. On GSM8K, GLM-4-Air leads at 90.9% vs Mistral NeMo Minitron 8B at 58.45%.