Compare AI models

Specifications
Parameters
51B1.5B/7B/72B
Context window
128k4k
Benchmarks
GSM8K
91.43%96.7%
Overview
CompanyNVIDIAQwen
Release dateSep 23 2024Aug 8 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2-Math leads Llama 3.1 Nemotron 51B on 1 of the 1 benchmark they both report (GSM8K). Qwen2-Math shipped 46 days before Llama 3.1 Nemotron 51B, so benchmark comparisons should account for the intervening progress.

Llama 3.1 Nemotron 51B has 51B parameters, while Qwen2-Math has 1.5B/7B/72B. Context windows are 128k (Llama 3.1 Nemotron 51B) vs 4k (Qwen2-Math).

On GSM8K, Qwen2-Math leads at 96.7% vs Llama 3.1 Nemotron 51B at 91.43%.