Compare AI models

Specifications
Context window
200k128k
Benchmarks
HumanEval
88.1%75.7%
MMLU
80.9%81.9%
Overview
CompanyAnthropicZ.ai
Release dateOct 22 2024Jun 5 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Claude 3.5 Haiku and GLM-4-Air are evenly matched across the 2 benchmarks they both report (HumanEval, MMLU). GLM-4-Air shipped 139 days before Claude 3.5 Haiku, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3.5 Haiku) vs 128k (GLM-4-Air).

On HumanEval, Claude 3.5 Haiku leads at 88.1% vs GLM-4-Air at 75.7%. On MMLU, GLM-4-Air leads at 81.9% vs Claude 3.5 Haiku at 80.9%.