Compare AI models

Specifications
Parameters
2B/7B—
Context window
8k1M
Benchmarks
HumanEval
32.3%86.6%
MATH
24.3%81.1%
GSM8K
46.4%93.8%
Overview
CompanyGoogleQwen
Release dateFeb 21 2024Nov 15 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Turbo (1M) leads Gemma 1 on 3 of the 3 benchmarks they both report (HumanEval, MATH, GSM8K). Gemma 1 shipped 268 days before Qwen2.5-Turbo (1M), so benchmark comparisons should account for the intervening progress.

Context windows are 8k (Gemma 1) vs 1M (Qwen2.5-Turbo (1M)). Gemma 1 is open weight, while Qwen2.5-Turbo (1M) is closed.

On HumanEval, Qwen2.5-Turbo (1M) leads at 86.6% vs Gemma 1 at 32.3%. On MATH, Qwen2.5-Turbo (1M) leads at 81.1% vs Gemma 1 at 24.3%. On GSM8K, Qwen2.5-Turbo (1M) leads at 93.8% vs Gemma 1 at 46.4%.