Compare AI models

Specifications
Parameters
7B110B
Context window
8k32k
Benchmarks
HumanEval
26.2%52.4%
HellaSwag
81%87.5%
MMLU
62.5%80.4%
GSM8K
36.5%85.4%
Overview
CompanyMistralQwen
Release dateSep 27 2023Apr 25 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen1.5-110B leads Mistral 7B on 4 of the 4 benchmarks they both report (HumanEval, HellaSwag, MMLU, GSM8K). Mistral 7B shipped 211 days before Qwen1.5-110B, so benchmark comparisons should account for the intervening progress.

Mistral 7B has 7B parameters, while Qwen1.5-110B has 110B. Context windows are 8k (Mistral 7B) vs 32k (Qwen1.5-110B).

On HumanEval, Qwen1.5-110B leads at 52.4% vs Mistral 7B at 26.2%. On HellaSwag, Qwen1.5-110B leads at 87.5% vs Mistral 7B at 81%. On MMLU, Qwen1.5-110B leads at 80.4% vs Mistral 7B at 62.5%. On GSM8K, Qwen1.5-110B leads at 85.4% vs Mistral 7B at 36.5%.