Compare AI models

Specifications
Parameters
8B/70B/405B51B
Context window
128k128k
API pricing
Cheapest input
$0.02DeepInfra—
Cheapest output
$0.04DeepInfra—
$6.00DeepInfra · fp8—
Benchmarks
ARC-Challenge
96.9%69.2%
MMLU
87.3%80.2%
GSM8K
96.8%91.43%
Overview
CompanyMetaNVIDIA
Release dateJul 23 2024Sep 23 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 3.1 leads Llama 3.1 Nemotron 51B on 3 of the 3 benchmarks they both report (ARC-Challenge, MMLU, GSM8K). LLaMA 3.1 shipped 62 days before Llama 3.1 Nemotron 51B, so benchmark comparisons should account for the intervening progress.

LLaMA 3.1 has 8B/70B/405B parameters, while Llama 3.1 Nemotron 51B has 51B. Context windows are 128k (LLaMA 3.1) vs 128k (Llama 3.1 Nemotron 51B).

On ARC-Challenge, LLaMA 3.1 leads at 96.9% vs Llama 3.1 Nemotron 51B at 69.2%. On MMLU, LLaMA 3.1 leads at 87.3% vs Llama 3.1 Nemotron 51B at 80.2%. On GSM8K, LLaMA 3.1 leads at 96.8% vs Llama 3.1 Nemotron 51B at 91.43%.