Compare AI models

Specifications
Parameters
—6B
Context window
100k8k
Benchmarks
HumanEval
71.2%58.5%
MMLU
78.5%61.4%
GSM8K
88%72.3%
Overview
CompanyAnthropicZ.ai
Release dateJul 11 2023Oct 27 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude 2 leads ChatGLM3-6B on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Claude 2 shipped 108 days before ChatGLM3-6B, so benchmark comparisons should account for the intervening progress.

Context windows are 100k (Claude 2) vs 8k (ChatGLM3-6B). Claude 2 is closed, while ChatGLM3-6B is open weight.

On HumanEval, Claude 2 leads at 71.2% vs ChatGLM3-6B at 58.5%. On MMLU, Claude 2 leads at 78.5% vs ChatGLM3-6B at 61.4%. On GSM8K, Claude 2 leads at 88% vs ChatGLM3-6B at 72.3%.