Compare AI models

Specifications
Parameters
7B/13B/70B6B
Context window
4k32k
Benchmarks
HumanEval
29.9%9.8%
MATH
13.5%6.9%
HellaSwag
85.3%57%
MMLU
68.9%45.2%
GSM8K
56.8%25.9%
Overview
CompanyMetaZ.ai
Release dateJul 18 2023Jun 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 2 leads ChatGLM2-6B on 5 of the 5 benchmarks they both report. ChatGLM2-6B shipped 23 days before LLaMA 2, so benchmark comparisons should account for the intervening progress.

LLaMA 2 has 7B/13B/70B parameters, while ChatGLM2-6B has 6B. Context windows are 4k (LLaMA 2) vs 32k (ChatGLM2-6B).

On HumanEval, LLaMA 2 leads at 29.9% vs ChatGLM2-6B at 9.8%. On MATH, LLaMA 2 leads at 13.5% vs ChatGLM2-6B at 6.9%. On HellaSwag, LLaMA 2 leads at 85.3% vs ChatGLM2-6B at 57%. On MMLU, LLaMA 2 leads at 68.9% vs ChatGLM2-6B at 45.2%. On GSM8K, LLaMA 2 leads at 56.8% vs ChatGLM2-6B at 25.9%.