Compare AI models

Specifications
Parameters
—7B/14B
Context window
1M1M
Benchmarks
LiveCodeBench
30%38.6%
MATH
77.9%79.5%
MMLU-Pro
67.3%63.3%
Overview
CompanyGoogleQwen
Release dateSep 24 2024Jan 27 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-1M leads Gemini 1.5 Flash-002 on 2 of the 3 benchmarks they both report (LiveCodeBench, MATH, MMLU-Pro). Gemini 1.5 Flash-002 shipped 125 days before Qwen2.5-1M, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 1.5 Flash-002) vs 1M (Qwen2.5-1M). Gemini 1.5 Flash-002 is closed, while Qwen2.5-1M is open weight.

On LiveCodeBench, Qwen2.5-1M leads at 38.6% vs Gemini 1.5 Flash-002 at 30%. On MATH, Qwen2.5-1M leads at 79.5% vs Gemini 1.5 Flash-002 at 77.9%. On MMLU-Pro, Gemini 1.5 Flash-002 leads at 67.3% vs Qwen2.5-1M at 63.3%.