Compare AI models

Specifications
Parameters
—14B
Context window
1M2k
Benchmarks
HumanEval
74.3%32.3%
MATH
54.9%24.8%
MMLU
78.9%66.3%
GSM8K
86.2%61.3%
Overview
CompanyGoogleQwen
Release dateMay 14 2024Sep 25 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemini 1.5 Flash leads Qwen-14B on 4 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). Qwen-14B shipped 232 days before Gemini 1.5 Flash, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 1.5 Flash) vs 2k (Qwen-14B). Gemini 1.5 Flash is closed, while Qwen-14B is open weight.

On HumanEval, Gemini 1.5 Flash leads at 74.3% vs Qwen-14B at 32.3%. On MATH, Gemini 1.5 Flash leads at 54.9% vs Qwen-14B at 24.8%. On MMLU, Gemini 1.5 Flash leads at 78.9% vs Qwen-14B at 66.3%. On GSM8K, Gemini 1.5 Flash leads at 86.2% vs Qwen-14B at 61.3%.