Compare AI models

Specifications
Context window
200k—
Benchmarks
HumanEval
75.9%72%
MMLU
76.7%81.5%
GSM8K
88.9%87.6%
Overview
CompanyAnthropicZ.ai
Release dateMar 4 2024Jan 16 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Claude 3 Haiku leads GLM-4 on 2 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). GLM-4 shipped 48 days before Claude 3 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 Haiku leads at 75.9% vs GLM-4 at 72%. On MMLU, GLM-4 leads at 81.5% vs Claude 3 Haiku at 76.7%. On GSM8K, Claude 3 Haiku leads at 88.9% vs GLM-4 at 87.6%.