Compare AI models

Specifications
Parameters
7B/13B/34B—
Context window
16k1M
Benchmarks
HumanEval
48.8%86.6%
Overview
CompanyMetaQwen
Release dateAug 24 2023Nov 15 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Turbo (1M) leads Code Llama on 1 of the 1 benchmark they both report (HumanEval). Code Llama shipped 449 days before Qwen2.5-Turbo (1M), so benchmark comparisons should account for the intervening progress.

Context windows are 16k (Code Llama) vs 1M (Qwen2.5-Turbo (1M)). Code Llama is open weight, while Qwen2.5-Turbo (1M) is closed.

On HumanEval, Qwen2.5-Turbo (1M) leads at 86.6% vs Code Llama at 48.8%.