Nvidia Nemotron Super 49B

Llama-3.3-Nemotron-Super-49B-v1 is a model which offers a great tradeoff between model accuracy and efficiency. Efficiency (throughput) directly translates to savings. Using a novel Neural Architecture Search (NAS) approach, we greatly reduce the model's memory footprint, enabling larger workloads, as well as fitting the model on a single GPU at high workloads (H200). This NAS approach enables the selection of a desired point in the accuracy-efficiency tradeoff. For more information on the NAS approach, please refer to this paper.

Added Aug 8, 2025

Pricing

Auto routing · per 1M tokens

Input: $0.15
Output: $0.15

Compare provider prices

Specifications

Context window: 128K
Max output: 16.4K
Parameters: 49B

Benchmarks

Artificial Analysis

LMArena

Sourced from Artificial Analysis.

Intelligence Index

7.3

Better than 24% of models compared

Document reasoning

AA-LCR v1.1

Long context reasoning with updated grading

12.0%

Better than 17% of models compared

Reasoning

HLE

Humanity's Last Exam

3.8%

Better than 10% of models compared

IFBench

Instruction-following benchmark

39.5%

Better than 37% of models compared

Coding

Terminal-Bench Hard (legacy)

Legacy fallback · Agentic coding and terminal use

0.0%

Better than 5% of models compared

LiveCodeBench

Contamination-free coding benchmark

28.0%

Better than 31% of models compared

Math

AIME 2025

American Invitational Mathematics Examination 2025

7.7%

Better than 12% of models compared

AIME

American Invitational Mathematics Examination

19.3%

Better than 46% of models compared

Math-500

Diverse mathematical problem solving benchmark

77.5%

Better than 42% of models compared

Knowledge

MMLU-Pro

Professional and academic subject knowledge

69.8%

Better than 36% of models compared

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

51.7%

Better than 26% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation