Compare AI models

Specifications
Context window
200k128k
Benchmarks
HumanEval
73%75.7%
MMLU
81.5%81.9%
GSM8K
92.3%90.9%
Overview
CompanyAnthropicZ.ai
Release dateMar 4 2024Jun 5 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

GLM-4-Air leads Claude 3 Sonnet on 2 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Claude 3 Sonnet shipped 93 days before GLM-4-Air, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3 Sonnet) vs 128k (GLM-4-Air).

On HumanEval, GLM-4-Air leads at 75.7% vs Claude 3 Sonnet at 73%. On MMLU, GLM-4-Air leads at 81.9% vs Claude 3 Sonnet at 81.5%. On GSM8K, Claude 3 Sonnet leads at 92.3% vs GLM-4-Air at 90.9%.