Compare AI models

Specifications
Context window
200k—
Benchmarks
HumanEval
88.1%72%
MMLU
80.9%81.5%
Overview
CompanyAnthropicZ.ai
Release dateOct 22 2024Jan 16 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Claude 3.5 Haiku and GLM-4 are evenly matched across the 2 benchmarks they both report (HumanEval, MMLU). GLM-4 shipped 280 days before Claude 3.5 Haiku, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On HumanEval, Claude 3.5 Haiku leads at 88.1% vs GLM-4 at 72%. On MMLU, GLM-4 leads at 81.5% vs Claude 3.5 Haiku at 80.9%.