Compare AI models

Specifications
Parameters
—1.5B/7B/72B
Context window
128k4k
Benchmarks
MATH
64.3%84%
Overview
CompanyOpenAIQwen
Release dateNov 6 2023Aug 8 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2-Math leads GPT-4 Turbo on 1 of the 1 benchmark they both report (MATH). GPT-4 Turbo shipped 276 days before Qwen2-Math, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (GPT-4 Turbo) vs 4k (Qwen2-Math). GPT-4 Turbo is closed, while Qwen2-Math is open weight.

On MATH, Qwen2-Math leads at 84% vs GPT-4 Turbo at 64.3%.