Compare AI models

Specifications
Parameters
—14.3B
Context window
200k32k
Benchmarks
HumanEval
96.3%34.2%
MMLU
85.9%62.5%
Overview
CompanyOpenAIQwen
Release dateJan 31 2025Mar 28 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

o3-mini leads Qwen1.5-MoE on 2 of the 2 benchmarks they both report (HumanEval, MMLU). Qwen1.5-MoE shipped 309 days before o3-mini, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (o3-mini) vs 32k (Qwen1.5-MoE). o3-mini is closed, while Qwen1.5-MoE is open weight.

On HumanEval, o3-mini leads at 96.3% vs Qwen1.5-MoE at 34.2%. On MMLU, o3-mini leads at 85.9% vs Qwen1.5-MoE at 62.5%.