Compare AI models

Specifications
Parameters
—6B
Context window
200k8k
Benchmarks
HumanEval
84.9%58.5%
MMLU
88.2%61.4%
GSM8K
95%72.3%
Overview
CompanyAnthropicZ.ai
Release dateMar 4 2024Oct 27 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude 3 Opus leads ChatGLM3-6B on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). ChatGLM3-6B shipped 129 days before Claude 3 Opus, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3 Opus) vs 8k (ChatGLM3-6B). Claude 3 Opus is closed, while ChatGLM3-6B is open weight.

On HumanEval, Claude 3 Opus leads at 84.9% vs ChatGLM3-6B at 58.5%. On MMLU, Claude 3 Opus leads at 88.2% vs ChatGLM3-6B at 61.4%. On GSM8K, Claude 3 Opus leads at 95% vs ChatGLM3-6B at 72.3%.