Compare AI models

Specifications
Parameters
8B/70B6B
Context window
8k8k
Benchmarks
HumanEval
81.7%58.5%
MATH
50.4%25.7%
MMLU
82%61.4%
GSM8K
93%72.3%
Overview
CompanyMetaZ.ai
Release dateApr 18 2024Oct 27 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 3 (8B/70B) leads ChatGLM3-6B on 4 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). ChatGLM3-6B shipped 174 days before LLaMA 3 (8B/70B), so benchmark comparisons should account for the intervening progress.

LLaMA 3 (8B/70B) has 8B/70B parameters, while ChatGLM3-6B has 6B. Context windows are 8k (LLaMA 3 (8B/70B)) vs 8k (ChatGLM3-6B).

On HumanEval, LLaMA 3 (8B/70B) leads at 81.7% vs ChatGLM3-6B at 58.5%. On MATH, LLaMA 3 (8B/70B) leads at 50.4% vs ChatGLM3-6B at 25.7%. On MMLU, LLaMA 3 (8B/70B) leads at 82% vs ChatGLM3-6B at 61.4%. On GSM8K, LLaMA 3 (8B/70B) leads at 93% vs ChatGLM3-6B at 72.3%.