Compare AI models

Specifications
Parameters
51B0.5B/1.5B/3B/7B/14B/32B
Context window
128k128k
API pricing
Cheapest input
—$0.66Cloudflare
Cheapest output
—$1.00Cloudflare
—$182Cloudflare
Benchmarks
MMLU
80.2%77.6%
GSM8K
91.43%93%
Overview
CompanyNVIDIAQwen
Release dateSep 23 2024Sep 19 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Llama 3.1 Nemotron 51B and Qwen2.5-Coder are evenly matched across the 2 benchmarks they both report (MMLU, GSM8K). Qwen2.5-Coder shipped 4 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 Qwen2.5-Coder has 0.5B/1.5B/3B/7B/14B/32B. Context windows are 128k (Llama 3.1 Nemotron 51B) vs 128k (Qwen2.5-Coder).

On MMLU, Llama 3.1 Nemotron 51B leads at 80.2% vs Qwen2.5-Coder at 77.6%. On GSM8K, Qwen2.5-Coder leads at 93% vs Llama 3.1 Nemotron 51B at 91.43%.