Compare AI models

Specifications
Context window
200k—
Benchmarks
HumanEval
73%72%
MMLU
81.5%81.5%
GSM8K
92.3%87.6%
Overview
CompanyAnthropicZ.ai
Release dateMar 4 2024Jan 16 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Claude 3 Sonnet leads GLM-4 on 2 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). GLM-4 shipped 48 days before Claude 3 Sonnet, 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 Sonnet leads at 73% vs GLM-4 at 72%. On MMLU, both models score 81.5%. On GSM8K, Claude 3 Sonnet leads at 92.3% vs GLM-4 at 87.6%.