Compare AI models

Specifications
Parameters
—7B/14B
Context window
1M1M
Benchmarks
HumanEval
71.9%88.4%
MATH
58.5%79.5%
GSM8K
91.7%94.8%
Overview
CompanyGoogleQwen
Release dateFeb 15 2024Jan 27 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-1M leads Gemini 1.5 Pro on 3 of the 3 benchmarks they both report (HumanEval, MATH, GSM8K). Gemini 1.5 Pro shipped 347 days before Qwen2.5-1M, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 1.5 Pro) vs 1M (Qwen2.5-1M). Gemini 1.5 Pro is closed, while Qwen2.5-1M is open weight.

On HumanEval, Qwen2.5-1M leads at 88.4% vs Gemini 1.5 Pro at 71.9%. On MATH, Qwen2.5-1M leads at 79.5% vs Gemini 1.5 Pro at 58.5%. On GSM8K, Qwen2.5-1M leads at 94.8% vs Gemini 1.5 Pro at 91.7%.