Compare AI models

Specifications
Context window
200k128k
Benchmarks
HumanEval
84.9%75.7%
MMLU
88.2%81.9%
GSM8K
95%90.9%
Overview
CompanyAnthropicZ.ai
Release dateMar 4 2024Jun 5 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

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

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

On HumanEval, Claude 3 Opus leads at 84.9% vs GLM-4-Air at 75.7%. On MMLU, Claude 3 Opus leads at 88.2% vs GLM-4-Air at 81.9%. On GSM8K, Claude 3 Opus leads at 95% vs GLM-4-Air at 90.9%.