Compare AI models

Specifications
Parameters
7B/13B/33B/65B110B
Context window
2k32k
Benchmarks
HumanEval
23.7%52.4%
MATH
10.6%49.6%
HellaSwag
84.2%87.5%
MMLU
63.4%80.4%
GSM8K
50.9%85.4%
Overview
CompanyMetaQwen
Release dateFeb 24 2023Apr 25 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen1.5-110B leads LLaMA 1 on 5 of the 5 benchmarks they both report. LLaMA 1 shipped 426 days before Qwen1.5-110B, so benchmark comparisons should account for the intervening progress.

LLaMA 1 has 7B/13B/33B/65B parameters, while Qwen1.5-110B has 110B. Context windows are 2k (LLaMA 1) vs 32k (Qwen1.5-110B).

On HumanEval, Qwen1.5-110B leads at 52.4% vs LLaMA 1 at 23.7%. On MATH, Qwen1.5-110B leads at 49.6% vs LLaMA 1 at 10.6%. On HellaSwag, Qwen1.5-110B leads at 87.5% vs LLaMA 1 at 84.2%. On MMLU, Qwen1.5-110B leads at 80.4% vs LLaMA 1 at 63.4%. On GSM8K, Qwen1.5-110B leads at 85.4% vs LLaMA 1 at 50.9%.