Compare AI models

Specifications
Parameters
14.3B6B
Context window
32k8k
Benchmarks
HumanEval
34.2%35.9%
Overview
CompanyQwenZ.ai
Release dateMar 28 2024Jul 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

CodeGeeX2-6B leads Qwen1.5-MoE on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX2-6B shipped 247 days before Qwen1.5-MoE, so benchmark comparisons should account for the intervening progress.

Qwen1.5-MoE has 14.3B parameters, while CodeGeeX2-6B has 6B. Context windows are 32k (Qwen1.5-MoE) vs 8k (CodeGeeX2-6B).

On HumanEval, CodeGeeX2-6B leads at 35.9% vs Qwen1.5-MoE at 34.2%.