Compare AI models

Specifications
Parameters
—6B
Context window
200k8k
Benchmarks
HumanEval
88.1%58.5%
MMLU
80.9%61.4%
Overview
CompanyAnthropicZ.ai
Release dateOct 22 2024Oct 27 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude 3.5 Haiku leads ChatGLM3-6B on 2 of the 2 benchmarks they both report (HumanEval, MMLU). ChatGLM3-6B shipped 361 days before Claude 3.5 Haiku, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3.5 Haiku) vs 8k (ChatGLM3-6B). Claude 3.5 Haiku is closed, while ChatGLM3-6B is open weight.

On HumanEval, Claude 3.5 Haiku leads at 88.1% vs ChatGLM3-6B at 58.5%. On MMLU, Claude 3.5 Haiku leads at 80.9% vs ChatGLM3-6B at 61.4%.