Compare AI models

Specifications
Parameters
—6B
Context window
100k32k
Benchmarks
HumanEval
58.7%9.8%
GSM8K
86.7%25.9%
Overview
CompanyAnthropicZ.ai
Release dateAug 9 2023Jun 25 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude Instant 1.2 leads ChatGLM2-6B on 2 of the 2 benchmarks they both report (HumanEval, GSM8K). ChatGLM2-6B shipped 45 days before Claude Instant 1.2, so benchmark comparisons should account for the intervening progress.

Context windows are 100k (Claude Instant 1.2) vs 32k (ChatGLM2-6B). Claude Instant 1.2 is closed, while ChatGLM2-6B is open weight.

On HumanEval, Claude Instant 1.2 leads at 58.7% vs ChatGLM2-6B at 9.8%. On GSM8K, Claude Instant 1.2 leads at 86.7% vs ChatGLM2-6B at 25.9%.