Compare AI models

Specifications
Parameters
340B14B
Context window
4k2k
Benchmarks
HumanEval
73.2%32.3%
MMLU
78.7%66.3%
GSM8K
92.3%61.3%
Overview
CompanyNVIDIAQwen
Release dateJun 14 2024Sep 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Nemotron-4 340B leads Qwen-14B on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Qwen-14B shipped 263 days before Nemotron-4 340B, so benchmark comparisons should account for the intervening progress.

Nemotron-4 340B has 340B parameters, while Qwen-14B has 14B. Context windows are 4k (Nemotron-4 340B) vs 2k (Qwen-14B).

On HumanEval, Nemotron-4 340B leads at 73.2% vs Qwen-14B at 32.3%. On MMLU, Nemotron-4 340B leads at 78.7% vs Qwen-14B at 66.3%. On GSM8K, Nemotron-4 340B leads at 92.3% vs Qwen-14B at 61.3%.