Compare AI models

Specifications
Parameters
—9B
Context window
1M128k
Benchmarks
HumanEval
86.6%71.8%
MATH
81.1%50.6%
GSM8K
93.8%79.6%
Overview
CompanyQwenZ.ai
Release dateNov 15 2024Jun 5 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Turbo (1M) leads GLM-4-9B on 3 of the 3 benchmarks they both report (HumanEval, MATH, GSM8K). GLM-4-9B shipped 163 days before Qwen2.5-Turbo (1M), so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Qwen2.5-Turbo (1M)) vs 128k (GLM-4-9B). Qwen2.5-Turbo (1M) is closed, while GLM-4-9B is open weight.

On HumanEval, Qwen2.5-Turbo (1M) leads at 86.6% vs GLM-4-9B at 71.8%. On MATH, Qwen2.5-Turbo (1M) leads at 81.1% vs GLM-4-9B at 50.6%. On GSM8K, Qwen2.5-Turbo (1M) leads at 93.8% vs GLM-4-9B at 79.6%.