NVIDIA Nemotron 3.5 Super VL - It Powers Specialized Agents with Multimodal Reasoning

by•
Our new open model combines reasoning and tool use with text, image, document, and video understanding for long-running AI agents.

Add a comment

Replies

Best
Hunter
📌

I’m happy to share this! NVIDIA Nemotron 3.5 Super VL is a big step forward for open AI models and intelligent agents.

It combines reasoning, tool use, and multimodal understanding in one model:

  • Advanced reasoning and tool use

  • Understands text, images, documents, and videos

  • Completes 10,000 coding tasks up to 4× faster while maintaining strong SWE-Bench Pro accuracy

  • High output speed, even with 100K input tokens

  • Adaptable for finance, cybersecurity, scientific research, and more

With 120B total parameters and 12B active parameters, it’s designed to help AI agents handle complex, long-running tasks with greater efficiency.

Exciting to see open models pushing AI agents forward!