Compare AI models

Specifications
Parameters
1.5B/7B/8B/14B/32B/70B49B
Context window
—128k
Benchmarks
LiveCodeBench
57.5%73.58%
MATH-500
94.5%97.4%
AIME 2024
70%87.5%
GPQA Diamond
65.2%71.97%
Overview
CompanyDeepSeekNVIDIA
Release dateJan 20 2025Jul 25 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Llama Nemotron Super 49B v1.5 leads DeepSeek R1 Distill on 4 of the 4 benchmarks they both report (LiveCodeBench, MATH-500, AIME 2024, GPQA Diamond). DeepSeek R1 Distill shipped 186 days before Llama Nemotron Super 49B v1.5, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 Distill has 1.5B/7B/8B/14B/32B/70B parameters, while Llama Nemotron Super 49B v1.5 has 49B.

On LiveCodeBench, Llama Nemotron Super 49B v1.5 leads at 73.58% vs DeepSeek R1 Distill at 57.5%. On MATH-500, Llama Nemotron Super 49B v1.5 leads at 97.4% vs DeepSeek R1 Distill at 94.5%. On AIME 2024, Llama Nemotron Super 49B v1.5 leads at 87.5% vs DeepSeek R1 Distill at 70%. On GPQA Diamond, Llama Nemotron Super 49B v1.5 leads at 71.97% vs DeepSeek R1 Distill at 65.2%.