Compare AI models

Specifications
Parameters
8B/70B7B
Context window
8k64k
Benchmarks
HumanEval
81.7%83.5%
Overview
CompanyMetaQwen
Release dateApr 18 2024Apr 16 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

CodeQwen1.5 leads LLaMA 3 (8B/70B) on 1 of the 1 benchmark they both report (HumanEval). CodeQwen1.5 shipped 2 days before LLaMA 3 (8B/70B), so benchmark comparisons should account for the intervening progress.

LLaMA 3 (8B/70B) has 8B/70B parameters, while CodeQwen1.5 has 7B. Context windows are 8k (LLaMA 3 (8B/70B)) vs 64k (CodeQwen1.5).

On HumanEval, CodeQwen1.5 leads at 83.5% vs LLaMA 3 (8B/70B) at 81.7%.