Compare AI models

Specifications
Parameters
7B110B
Context window
2k32k
Benchmarks
HumanEval
24.4%52.4%
MMLU
56.7%80.4%
GSM8K
51.6%85.4%
Overview
CompanyQwenQwen
Release dateAug 3 2023Apr 25 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen1.5-110B leads Qwen-7B on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Qwen-7B shipped 266 days before Qwen1.5-110B, so benchmark comparisons should account for the intervening progress.

Qwen-7B has 7B parameters, while Qwen1.5-110B has 110B. Context windows are 2k (Qwen-7B) vs 32k (Qwen1.5-110B).

On HumanEval, Qwen1.5-110B leads at 52.4% vs Qwen-7B at 24.4%. On MMLU, Qwen1.5-110B leads at 80.4% vs Qwen-7B at 56.7%. On GSM8K, Qwen1.5-110B leads at 85.4% vs Qwen-7B at 51.6%.