Compare AI models

Specifications
Parameters
49B—
Context window
128k128k
Benchmarks
MATH-500
97.4%85.5%
AIME 2024
87.5%44.6%
GPQA Diamond
71.97%73.3%
Overview
CompanyNVIDIAOpenAI
Release dateJul 25 2025Sep 12 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Llama Nemotron Super 49B v1.5 leads o1-preview on 2 of the 3 benchmarks they both report (MATH-500, AIME 2024, GPQA Diamond). o1-preview shipped 316 days before Llama Nemotron Super 49B v1.5, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Llama Nemotron Super 49B v1.5) vs 128k (o1-preview). Llama Nemotron Super 49B v1.5 is open weight, while o1-preview is closed.

On MATH-500, Llama Nemotron Super 49B v1.5 leads at 97.4% vs o1-preview at 85.5%. On AIME 2024, Llama Nemotron Super 49B v1.5 leads at 87.5% vs o1-preview at 44.6%. On GPQA Diamond, o1-preview leads at 73.3% vs Llama Nemotron Super 49B v1.5 at 71.97%.