Compare AI models

Specifications
Parameters
51B0.5B/1.8B/4B/7B/14B/72B
Context window
128k32k
Benchmarks
MMLU
80.2%75.6%
GSM8K
91.43%82.7%
Overview
CompanyNVIDIAQwen
Release dateSep 23 2024Feb 4 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Llama 3.1 Nemotron 51B leads Qwen1.5 on 2 of the 2 benchmarks they both report (MMLU, GSM8K). Qwen1.5 shipped 232 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 Qwen1.5 has 0.5B/1.8B/4B/7B/14B/72B. Context windows are 128k (Llama 3.1 Nemotron 51B) vs 32k (Qwen1.5).

On MMLU, Llama 3.1 Nemotron 51B leads at 80.2% vs Qwen1.5 at 75.6%. On GSM8K, Llama 3.1 Nemotron 51B leads at 91.43% vs Qwen1.5 at 82.7%.