Compare AI models

Specifications
Parameters
—51B
Context window
200k128k
Benchmarks
MMLU
76.7%80.2%
GSM8K
88.9%91.43%
Overview
CompanyAnthropicNVIDIA
Release dateMar 4 2024Sep 23 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Llama 3.1 Nemotron 51B leads Claude 3 Haiku on 2 of the 2 benchmarks they both report (MMLU, GSM8K). Claude 3 Haiku shipped 203 days before Llama 3.1 Nemotron 51B, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3 Haiku) vs 128k (Llama 3.1 Nemotron 51B). Claude 3 Haiku is closed, while Llama 3.1 Nemotron 51B is open weight.

On MMLU, Llama 3.1 Nemotron 51B leads at 80.2% vs Claude 3 Haiku at 76.7%. On GSM8K, Llama 3.1 Nemotron 51B leads at 91.43% vs Claude 3 Haiku at 88.9%.