Compare AI models

Specifications
Parameters
1.8B/3.25B14B
Context window
32k2k
Benchmarks
MATH
22.8%24.8%
MMLU
55.8%66.3%
Overview
CompanyGoogleQwen
Release dateDec 6 2023Sep 25 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen-14B leads Gemini 1.0 Nano on 2 of the 2 benchmarks they both report (MATH, MMLU). Qwen-14B shipped 72 days before Gemini 1.0 Nano, so benchmark comparisons should account for the intervening progress.

Gemini 1.0 Nano has 1.8B/3.25B parameters, while Qwen-14B has 14B. Context windows are 32k (Gemini 1.0 Nano) vs 2k (Qwen-14B). Gemini 1.0 Nano is closed, while Qwen-14B is open weight.

On MATH, Qwen-14B leads at 24.8% vs Gemini 1.0 Nano at 22.8%. On MMLU, Qwen-14B leads at 66.3% vs Gemini 1.0 Nano at 55.8%.