Compare AI models

Specifications
Parameters
110B6B
Context window
32k8k
Benchmarks
HumanEval
52.4%58.5%
MATH
49.6%25.7%
HellaSwag
87.5%79.7%
MMLU
80.4%61.4%
GSM8K
85.4%72.3%
Overview
CompanyQwenZ.ai
Release dateApr 25 2024Oct 27 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen1.5-110B leads ChatGLM3-6B on 4 of the 5 benchmarks they both report. ChatGLM3-6B shipped 181 days before Qwen1.5-110B, so benchmark comparisons should account for the intervening progress.

Qwen1.5-110B has 110B parameters, while ChatGLM3-6B has 6B. Context windows are 32k (Qwen1.5-110B) vs 8k (ChatGLM3-6B).

On HumanEval, ChatGLM3-6B leads at 58.5% vs Qwen1.5-110B at 52.4%. On MATH, Qwen1.5-110B leads at 49.6% vs ChatGLM3-6B at 25.7%. On HellaSwag, Qwen1.5-110B leads at 87.5% vs ChatGLM3-6B at 79.7%. On MMLU, Qwen1.5-110B leads at 80.4% vs ChatGLM3-6B at 61.4%. On GSM8K, Qwen1.5-110B leads at 85.4% vs ChatGLM3-6B at 72.3%.