Compare AI models

Specifications
Parameters
0.5B/1.5B/3B/7B/14B/32B/72B—
Context window
128k128k
API pricing
Cheapest input
$0.288DeepInfra—
Cheapest output
$0.32DeepInfra—
$92.00DeepInfra · fp8—
Benchmarks
HumanEval
86.6%75.7%
IFEval
84.1%75.2%
MATH
83.1%57.9%
GSM8K
95.8%90.9%
Overview
CompanyQwenZ.ai
Release dateSep 19 2024Jun 5 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen2.5 leads GLM-4-Air on 4 of the 4 benchmarks they both report (HumanEval, IFEval, MATH, GSM8K). GLM-4-Air shipped 106 days before Qwen2.5, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Qwen2.5) vs 128k (GLM-4-Air). Qwen2.5 is open weight, while GLM-4-Air is closed.

On HumanEval, Qwen2.5 leads at 86.6% vs GLM-4-Air at 75.7%. On IFEval, Qwen2.5 leads at 84.1% vs GLM-4-Air at 75.2%. On MATH, Qwen2.5 leads at 83.1% vs GLM-4-Air at 57.9%. On GSM8K, Qwen2.5 leads at 95.8% vs GLM-4-Air at 90.9%.