Compare AI models

Specifications
Parameters
8B/70B/405B6B
Context window
128k8k
API pricing
Cheapest input
$0.02DeepInfra—
Cheapest output
$0.04DeepInfra—
$6.00DeepInfra · fp8—
Benchmarks
HumanEval
89%58.5%
MATH
73.8%25.7%
MMLU
87.3%61.4%
GSM8K
96.8%72.3%
Overview
CompanyMetaZ.ai
Release dateJul 23 2024Oct 27 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 3.1 leads ChatGLM3-6B on 4 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). ChatGLM3-6B shipped 270 days before LLaMA 3.1, so benchmark comparisons should account for the intervening progress.

LLaMA 3.1 has 8B/70B/405B parameters, while ChatGLM3-6B has 6B. Context windows are 128k (LLaMA 3.1) vs 8k (ChatGLM3-6B).

On HumanEval, LLaMA 3.1 leads at 89% vs ChatGLM3-6B at 58.5%. On MATH, LLaMA 3.1 leads at 73.8% vs ChatGLM3-6B at 25.7%. On MMLU, LLaMA 3.1 leads at 87.3% vs ChatGLM3-6B at 61.4%. On GSM8K, LLaMA 3.1 leads at 96.8% vs ChatGLM3-6B at 72.3%.