Compare AI models

Specifications
Parameters
70B8B
Context window
128k8k
API pricing
Cheapest input
$0.10DeepInfra—
Cheapest output
$0.32DeepInfra—
$36.00DeepInfra · turbo · fp8—
Benchmarks
HumanEval
88.4%36.22%
MMLU
86%69.51%
Overview
CompanyMetaNVIDIA
Release dateDec 6 2024Aug 21 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 3.3 leads Mistral NeMo Minitron 8B on 2 of the 2 benchmarks they both report (HumanEval, MMLU). Mistral NeMo Minitron 8B shipped 107 days before LLaMA 3.3, so benchmark comparisons should account for the intervening progress.

LLaMA 3.3 has 70B parameters, while Mistral NeMo Minitron 8B has 8B. Context windows are 128k (LLaMA 3.3) vs 8k (Mistral NeMo Minitron 8B).

On HumanEval, LLaMA 3.3 leads at 88.4% vs Mistral NeMo Minitron 8B at 36.22%. On MMLU, LLaMA 3.3 leads at 86% vs Mistral NeMo Minitron 8B at 69.51%.