Compare AI models

Specifications
Parameters
47B—
Context window
32k1M
Benchmarks
HumanEval
40.2%86.6%
GSM8K
58.4%93.8%
Overview
CompanyMistralQwen
Release dateDec 8 2023Nov 15 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Turbo (1M) leads Mixtral 8×7B on 2 of the 2 benchmarks they both report (HumanEval, GSM8K). Mixtral 8×7B shipped 343 days before Qwen2.5-Turbo (1M), so benchmark comparisons should account for the intervening progress.

Context windows are 32k (Mixtral 8×7B) vs 1M (Qwen2.5-Turbo (1M)). Mixtral 8×7B is open weight, while Qwen2.5-Turbo (1M) is closed.

On HumanEval, Qwen2.5-Turbo (1M) leads at 86.6% vs Mixtral 8×7B at 40.2%. On GSM8K, Qwen2.5-Turbo (1M) leads at 93.8% vs Mixtral 8×7B at 58.4%.