Compare AI models

Specifications
Parameters
8B/70B/405B—
Context window
128k128k
API pricing
Cheapest input
$0.02DeepInfra—
Cheapest output
$0.04DeepInfra—
$6.00DeepInfra · fp8—
Benchmarks
HumanEval
89%75.7%
MATH
73.8%57.9%
MMLU
87.3%81.9%
GSM8K
96.8%90.9%
Overview
CompanyMetaZ.ai
Release dateJul 23 2024Jun 5 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

LLaMA 3.1 leads GLM-4-Air on 4 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). GLM-4-Air shipped 48 days before LLaMA 3.1, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (LLaMA 3.1) vs 128k (GLM-4-Air). LLaMA 3.1 is open weight, while GLM-4-Air is closed.

On HumanEval, LLaMA 3.1 leads at 89% vs GLM-4-Air at 75.7%. On MATH, LLaMA 3.1 leads at 73.8% vs GLM-4-Air at 57.9%. On MMLU, LLaMA 3.1 leads at 87.3% vs GLM-4-Air at 81.9%. On GSM8K, LLaMA 3.1 leads at 96.8% vs GLM-4-Air at 90.9%.