Compare AI models

Specifications
Parameters
2B/7B7B/14B
Context window
8k1M
Benchmarks
HumanEval
32.3%88.4%
MATH
24.3%79.5%
GSM8K
46.4%94.8%
Overview
CompanyGoogleQwen
Release dateFeb 21 2024Jan 27 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-1M leads Gemma 1 on 3 of the 3 benchmarks they both report (HumanEval, MATH, GSM8K). Gemma 1 shipped 341 days before Qwen2.5-1M, so benchmark comparisons should account for the intervening progress.

Gemma 1 has 2B/7B parameters, while Qwen2.5-1M has 7B/14B. Context windows are 8k (Gemma 1) vs 1M (Qwen2.5-1M).

On HumanEval, Qwen2.5-1M leads at 88.4% vs Gemma 1 at 32.3%. On MATH, Qwen2.5-1M leads at 79.5% vs Gemma 1 at 24.3%. On GSM8K, Qwen2.5-1M leads at 94.8% vs Gemma 1 at 46.4%.