Compare AI models

Specifications
Parameters
110B6B
Context window
32k32k
Benchmarks
HumanEval
52.4%9.8%
MATH
49.6%6.9%
HellaSwag
87.5%57%
MMLU
80.4%45.2%
GSM8K
85.4%25.9%
Overview
CompanyQwenZ.ai
Release dateApr 25 2024Jun 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen1.5-110B leads ChatGLM2-6B on 5 of the 5 benchmarks they both report. ChatGLM2-6B shipped 305 days before Qwen1.5-110B, so benchmark comparisons should account for the intervening progress.

Qwen1.5-110B has 110B parameters, while ChatGLM2-6B has 6B. Context windows are 32k (Qwen1.5-110B) vs 32k (ChatGLM2-6B).

On HumanEval, Qwen1.5-110B leads at 52.4% vs ChatGLM2-6B at 9.8%. On MATH, Qwen1.5-110B leads at 49.6% vs ChatGLM2-6B at 6.9%. On HellaSwag, Qwen1.5-110B leads at 87.5% vs ChatGLM2-6B at 57%. On MMLU, Qwen1.5-110B leads at 80.4% vs ChatGLM2-6B at 45.2%. On GSM8K, Qwen1.5-110B leads at 85.4% vs ChatGLM2-6B at 25.9%.