Compare AI models

Specifications
Parameters
51B0.5B/1.5B/3B/7B/14B/32B/72B
Context window
128k128k
API pricing
Cheapest input
—$0.288DeepInfra
Cheapest output
—$0.32DeepInfra
—$92.00DeepInfra · fp8
Benchmarks
GSM8K
91.43%95.8%
Overview
CompanyNVIDIAQwen
Release dateSep 23 2024Sep 19 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5 leads Llama 3.1 Nemotron 51B on 1 of the 1 benchmark they both report (GSM8K). Qwen2.5 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 has 0.5B/1.5B/3B/7B/14B/32B/72B. Context windows are 128k (Llama 3.1 Nemotron 51B) vs 128k (Qwen2.5).

On GSM8K, Qwen2.5 leads at 95.8% vs Llama 3.1 Nemotron 51B at 91.43%.