Compare AI models

Specifications
Parameters
—49B
Context window
128k128k
Benchmarks
LiveCodeBench
62.5%73.58%
MATH-500
96.2%97.4%
AIME 2024
77.5%87.5%
Overview
CompanyMoonshot AINVIDIA
Release dateJan 20 2025Jul 25 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Llama Nemotron Super 49B v1.5 leads Kimi K1.5 on 3 of the 3 benchmarks they both report (LiveCodeBench, MATH-500, AIME 2024). Kimi K1.5 shipped 186 days before Llama Nemotron Super 49B v1.5, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Kimi K1.5) vs 128k (Llama Nemotron Super 49B v1.5). Kimi K1.5 is closed, while Llama Nemotron Super 49B v1.5 is open weight.

On LiveCodeBench, Llama Nemotron Super 49B v1.5 leads at 73.58% vs Kimi K1.5 at 62.5%. On MATH-500, Llama Nemotron Super 49B v1.5 leads at 97.4% vs Kimi K1.5 at 96.2%. On AIME 2024, Llama Nemotron Super 49B v1.5 leads at 87.5% vs Kimi K1.5 at 77.5%.