Compare AI models

Specifications
Parameters
340B—
Context window
4k1M
Benchmarks
HumanEval
73.2%86.6%
IFEval
79.9%76.3%
GSM8K
92.3%93.8%
Overview
CompanyNVIDIAQwen
Release dateJun 14 2024Nov 15 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Turbo (1M) leads Nemotron-4 340B on 2 of the 3 benchmarks they both report (HumanEval, IFEval, GSM8K). Nemotron-4 340B shipped 154 days before Qwen2.5-Turbo (1M), so benchmark comparisons should account for the intervening progress.

Context windows are 4k (Nemotron-4 340B) vs 1M (Qwen2.5-Turbo (1M)). Nemotron-4 340B is open weight, while Qwen2.5-Turbo (1M) is closed.

On HumanEval, Qwen2.5-Turbo (1M) leads at 86.6% vs Nemotron-4 340B at 73.2%. On IFEval, Nemotron-4 340B leads at 79.9% vs Qwen2.5-Turbo (1M) at 76.3%. On GSM8K, Qwen2.5-Turbo (1M) leads at 93.8% vs Nemotron-4 340B at 92.3%.