Compare AI models

Specifications
Parameters
8B/70B/405B1.5B/4B
Context window
128k8k
API pricing
Cheapest input
$0.02DeepInfra—
Cheapest output
$0.04DeepInfra—
$6.00DeepInfra · fp8—
Benchmarks
MMLU
87.3%54.84%
GSM8K
96.8%54.89%
Overview
CompanyMetaZ.ai
Release dateJul 23 2024Nov 29 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 3.1 leads GLM-Edge on 2 of the 2 benchmarks they both report (MMLU, GSM8K). LLaMA 3.1 shipped 129 days before GLM-Edge, so benchmark comparisons should account for the intervening progress.

LLaMA 3.1 has 8B/70B/405B parameters, while GLM-Edge has 1.5B/4B. Context windows are 128k (LLaMA 3.1) vs 8k (GLM-Edge).

On MMLU, LLaMA 3.1 leads at 87.3% vs GLM-Edge at 54.84%. On GSM8K, LLaMA 3.1 leads at 96.8% vs GLM-Edge at 54.89%.