Toggle navigation
shortly

NVIDIA

Available in Shortly AI

NVIDIA Nemotron 3 Super 120B A12B

Released March 11, 2026

ReasoningTool Use

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. It delivers up to 7x higher throughput, providing fast, cost-efficient inference for agentic tasks. Additionally, a long context window gives the model long-term memory, preventing AI agents from losing focus on long, multi-step tasks and ensuring high-accuracy results. Fully open with weights, datasets, and recipes, Super allows easy customization and secure deployment anywhere.

Try out now
Context window
256K tokens
Maximum output
32K tokens
Input pricing
$0.15/M
Output pricing
$0.65/M

Independent benchmark

LiveBench historical snapshot

32.5overall

Historical benchmark data from LiveBench, release 2026-01-08. Scores are pinned and are not fetched on page load.

NVIDIA Nemotron 3 Super 120B A12B LiveBench category scores
CategoryScore
Reasoning34.389
Coding54.072
Agentic Coding23.000
Mathematics36.429
Data Analysis21.231
Language30.042
Instruction Following28.408

Benchmarks measure selected evaluation tasks and do not guarantee performance for every prompt or workflow.

FAQ

Similar AI models

Qwen 3.7 FlashAlibabaThe Qwen3.7 native vision-language Flash model series delivers a comprehensive upgrade over 3.6-Flash in multimodal understanding and agent execution. This model particularly excels in enhanced multimodal foundations with stronger universal object recognition, further improved real-world perception and spatial intelligence, significantly upgraded multimodal agent capabilities for Search Agent and CI Agent scenarios with more stable end-to-end task execution, as well as optimized multimodal coding for a smoother vibe coding experience.GPT 5.6 LunaOpenAIGPT-5.6 Luna is a fast, affordable GPT-5.6 model that brings strong capability at the lowest cost in the series.Hy3TencentTencent Hy3 is an open-source Mixture-of-Experts (MoE) large language model developed by Tencent's Hunyuan team. It has 295B total parameters, 21B active parameters, a 3.8B-parameter MTP layer, and a 256K context window. Hy3 is designed for agentic workflows, coding, reasoning, long-context understanding, tool-use scenarios, document analysis, and structured generation. The model improves on Hy3 Preview with stronger tool-call reliability, better output-format stability, improved long-context retention, and lower hallucination rates in Tencent's internal evaluations.

Available with one subscription

Start with NVIDIA Nemotron 3 Super 120B A12B in Shortly AI

Keep your conversations, files and model choices together in one workspace.

Try NVIDIA Nemotron 3 Super 120B A12B