Compare AI models

Specifications
Parameters
—6B
Context window
200k32k
Benchmarks
HumanEval
93.7%9.8%
MMLU
90.5%45.2%
Overview
CompanyAnthropicZ.ai
Release dateOct 22 2024Jun 25 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude 3.5 Sonnet (upgraded) leads ChatGLM2-6B on 2 of the 2 benchmarks they both report (HumanEval, MMLU). ChatGLM2-6B shipped 485 days before Claude 3.5 Sonnet (upgraded), so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3.5 Sonnet (upgraded)) vs 32k (ChatGLM2-6B). Claude 3.5 Sonnet (upgraded) is closed, while ChatGLM2-6B is open weight.

On HumanEval, Claude 3.5 Sonnet (upgraded) leads at 93.7% vs ChatGLM2-6B at 9.8%. On MMLU, Claude 3.5 Sonnet (upgraded) leads at 90.5% vs ChatGLM2-6B at 45.2%.