Compare AI models

Specifications
Parameters
—51B
Context window
200k128k
Benchmarks
MMLU
80.9%80.2%
Overview
CompanyAnthropicNVIDIA
Release dateOct 22 2024Sep 23 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude 3.5 Haiku leads Llama 3.1 Nemotron 51B on 1 of the 1 benchmark they both report (MMLU). Llama 3.1 Nemotron 51B shipped 29 days before Claude 3.5 Haiku, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3.5 Haiku) vs 128k (Llama 3.1 Nemotron 51B). Claude 3.5 Haiku is closed, while Llama 3.1 Nemotron 51B is open weight.

On MMLU, Claude 3.5 Haiku leads at 80.9% vs Llama 3.1 Nemotron 51B at 80.2%.