Compare AI models

Specifications
Parameters
7B/13B/33B/65B6B
Context window
2k8k
Benchmarks
HumanEval
23.7%58.5%
MATH
10.6%25.7%
HellaSwag
84.2%79.7%
MMLU
63.4%61.4%
GSM8K
50.9%72.3%
Overview
CompanyMetaZ.ai
Release dateFeb 24 2023Oct 27 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

ChatGLM3-6B leads LLaMA 1 on 3 of the 5 benchmarks they both report. LLaMA 1 shipped 245 days before ChatGLM3-6B, so benchmark comparisons should account for the intervening progress.

LLaMA 1 has 7B/13B/33B/65B parameters, while ChatGLM3-6B has 6B. Context windows are 2k (LLaMA 1) vs 8k (ChatGLM3-6B).

On HumanEval, ChatGLM3-6B leads at 58.5% vs LLaMA 1 at 23.7%. On MATH, ChatGLM3-6B leads at 25.7% vs LLaMA 1 at 10.6%. On HellaSwag, LLaMA 1 leads at 84.2% vs ChatGLM3-6B at 79.7%. On MMLU, LLaMA 1 leads at 63.4% vs ChatGLM3-6B at 61.4%. On GSM8K, ChatGLM3-6B leads at 72.3% vs LLaMA 1 at 50.9%.