Compare AI models

Specifications
Parameters
110B6B
Context window
32k8k
Benchmarks
HumanEval
52.4%35.9%
Overview
CompanyQwenZ.ai
Release dateApr 25 2024Jul 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen1.5-110B leads CodeGeeX2-6B on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX2-6B shipped 275 days before Qwen1.5-110B, so benchmark comparisons should account for the intervening progress.

Qwen1.5-110B has 110B parameters, while CodeGeeX2-6B has 6B. Context windows are 32k (Qwen1.5-110B) vs 8k (CodeGeeX2-6B).

On HumanEval, Qwen1.5-110B leads at 52.4% vs CodeGeeX2-6B at 35.9%.