Compare AI models

Specifications
Parameters
110B9B
Context window
32k128k
Benchmarks
HumanEval
52.4%71.8%
MATH
49.6%50.6%
MMLU
80.4%72.4%
GSM8K
85.4%79.6%
Overview
CompanyQwenZ.ai
Release dateApr 25 2024Jun 5 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen1.5-110B and GLM-4-9B are evenly matched across the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). Qwen1.5-110B shipped 41 days before GLM-4-9B, so benchmark comparisons should account for the intervening progress.

Qwen1.5-110B has 110B parameters, while GLM-4-9B has 9B. Context windows are 32k (Qwen1.5-110B) vs 128k (GLM-4-9B).

On HumanEval, GLM-4-9B leads at 71.8% vs Qwen1.5-110B at 52.4%. On MATH, GLM-4-9B leads at 50.6% vs Qwen1.5-110B at 49.6%. On MMLU, Qwen1.5-110B leads at 80.4% vs GLM-4-9B at 72.4%. On GSM8K, Qwen1.5-110B leads at 85.4% vs GLM-4-9B at 79.6%.