Provider logo

Nvidia Nemotron 70b

nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
Provider logo

Nvidia Nemotron 70b

nvidia/Llama-3.1-Nemotron-70B-Instruct-HF

Nvidia's latest Llama fine-tune optimized for instruction following. Early results hints that it might outperform models such as GPT-4o and Claude 3.5 Sonnet.

Added Apr 15, 2025

Context Window

16.4K

Max Output

8.2K

Input Price (Auto)

$0.36/1M

Output Price (Auto)

$0.41/1M

Cache Read (Auto)

$0.18/1M

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

7.4

Better than 22% of models compared

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

46.5%

Better than 21% of models compared

HLE

Humanity's Last Exam

4.2%

Better than 18% of models compared

IFBench

Instruction-following benchmark

30.7%

Better than 15% of models compared

T²-Bench Telecom

Conversational AI agents in dual-control scenarios

23.1%

Better than 25% of models compared

AA-LCR

Long context reasoning evaluation

7.3%

Better than 17% of models compared

Coding

SciCode

Python programming for scientific computing

23.3%

Better than 25% of models compared

Terminal-Bench Hard

Agentic coding and terminal use

4.5%

Better than 29% of models compared

LiveCodeBench

Contamination-free coding benchmark

16.9%

Better than 18% of models compared

Math

AIME 2025

American Invitational Mathematics Examination 2025

11.0%

Better than 14% of models compared

AIME

American Invitational Mathematics Examination

24.7%

Better than 52% of models compared

Math-500

Diverse mathematical problem solving benchmark

73.3%

Better than 34% of models compared

Knowledge

MMLU-Pro

Professional and academic subject knowledge

69.0%

Better than 33% of models compared

Last updated Aug 16, 2026

Artificial Analysis

Providers

Auto routing is available for this model. Explicit provider selection is not available.

Loading provider options…

Compare Nvidia Nemotron 70b with similar models from the same provider or model family.

Nvidia Nemotron Super 49B

nvidia/Llama-3.3-Nemotron-Super-49B-v1

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.

Nvidia Nemotron 3.5 Lightning

nvidia/nemotron-3.5-lightning

Nvidia Nemotron 3.5 Lightning is an open-weight 30B-A3B hybrid Mamba-Transformer mixture-of-experts model for high-throughput agentic, coding, tool-use, instruction-following, and long-context workloads. Thinking is disabled on this variant. Included in the NanoGPT subscription.

Nvidia Nemotron 3.5 Lightning Thinking

nvidia/nemotron-3.5-lightning:thinking

Nvidia Nemotron 3.5 Lightning is an open-weight 30B-A3B hybrid Mamba-Transformer mixture-of-experts model for high-throughput agentic, coding, tool-use, instruction-following, and long-context workloads. This variant enables its reasoning trace. Included in the NanoGPT subscription.

Nvidia Nemotron 3 Ultra 550B

nvidia/nemotron-3-ultra-550b-a55b

Nvidia's Nemotron 3 Ultra 550B A55B model from the Nemotron 3 family. It uses a hybrid Mamba-Transformer MoE architecture. Provider-specific context limits vary, with the longest current route supporting up to 1M context.

Nvidia Nemotron 3 Ultra 550B Thinking

nvidia/nemotron-3-ultra-550b-a55b:thinking

Nvidia's Nemotron 3 Ultra 550B A55B model from the Nemotron 3 family. It uses a hybrid Mamba-Transformer MoE architecture. Provider-specific context limits vary, with the longest current route supporting up to 1M context. Thinking enabled.

Nvidia Nemotron 3 Nano Omni

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning

Nvidia's Nemotron 3 Nano Omni 30B-A3B reasoning model. It accepts multimodal context on supported providers and returns text responses for perception and agentic workflows.