Compare AI models

Specifications
Parameters
24B49B
Context window
40k128k
Benchmarks
LiveCodeBench
55.84%73.58%
AIME 2024
70.68%87.5%
AIME 2025
62.76%82.71%
GPQA Diamond
68.18%71.97%
Overview
CompanyMistralNVIDIA
Release dateJun 10 2025Jul 25 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Llama Nemotron Super 49B v1.5 leads Magistral Small on 4 of the 4 benchmarks they both report (LiveCodeBench, AIME 2024, AIME 2025, GPQA Diamond). Magistral Small shipped 45 days before Llama Nemotron Super 49B v1.5, so benchmark comparisons should account for the intervening progress.

Magistral Small has 24B parameters, while Llama Nemotron Super 49B v1.5 has 49B. Context windows are 40k (Magistral Small) vs 128k (Llama Nemotron Super 49B v1.5).

On LiveCodeBench, Llama Nemotron Super 49B v1.5 leads at 73.58% vs Magistral Small at 55.84%. On AIME 2024, Llama Nemotron Super 49B v1.5 leads at 87.5% vs Magistral Small at 70.68%. On AIME 2025, Llama Nemotron Super 49B v1.5 leads at 82.71% vs Magistral Small at 62.76%. On GPQA Diamond, Llama Nemotron Super 49B v1.5 leads at 71.97% vs Magistral Small at 68.18%.