Compare AI models

Specifications
Parameters
14B9B
Context window
2k128k
Benchmarks
HumanEval
32.3%71.8%
MATH
24.8%50.6%
MMLU
66.3%72.4%
GSM8K
61.3%79.6%
Overview
CompanyQwenZ.ai
Release dateSep 25 2023Jun 5 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

GLM-4-9B leads Qwen-14B on 4 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). Qwen-14B shipped 254 days before GLM-4-9B, so benchmark comparisons should account for the intervening progress.

Qwen-14B has 14B parameters, while GLM-4-9B has 9B. Context windows are 2k (Qwen-14B) vs 128k (GLM-4-9B).

On HumanEval, GLM-4-9B leads at 71.8% vs Qwen-14B at 32.3%. On MATH, GLM-4-9B leads at 50.6% vs Qwen-14B at 24.8%. On MMLU, GLM-4-9B leads at 72.4% vs Qwen-14B at 66.3%. On GSM8K, GLM-4-9B leads at 79.6% vs Qwen-14B at 61.3%.