Compare AI models

Specifications
Parameters
8B/70B6B
Context window
8k32k
Benchmarks
HumanEval
81.7%9.8%
MATH
50.4%6.9%
MMLU
82%45.2%
GSM8K
93%25.9%
Overview
CompanyMetaZ.ai
Release dateApr 18 2024Jun 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 3 (8B/70B) leads ChatGLM2-6B on 4 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). ChatGLM2-6B shipped 298 days before LLaMA 3 (8B/70B), so benchmark comparisons should account for the intervening progress.

LLaMA 3 (8B/70B) has 8B/70B parameters, while ChatGLM2-6B has 6B. Context windows are 8k (LLaMA 3 (8B/70B)) vs 32k (ChatGLM2-6B).

On HumanEval, LLaMA 3 (8B/70B) leads at 81.7% vs ChatGLM2-6B at 9.8%. On MATH, LLaMA 3 (8B/70B) leads at 50.4% vs ChatGLM2-6B at 6.9%. On MMLU, LLaMA 3 (8B/70B) leads at 82% vs ChatGLM2-6B at 45.2%. On GSM8K, LLaMA 3 (8B/70B) leads at 93% vs ChatGLM2-6B at 25.9%.