Nvidiaactive

Nemotron 3.5 Super VL

Released at: October 15, 2026

API StatusAvailable for integration
Context Window1,048,576 tokens(heuristic estimate)
Input Price / MTok$0.15(heuristic estimate)
Output Price / MTok$0.50(heuristic estimate)

Model Overview

Nvidia · Active Model

  • Long-Context
  • API Available
  • Reported Benchmarks

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...

Developer
Nvidia(heuristic estimate)
Release Date
October 15, 2026(heuristic estimate)
Context Window
1,048,576 tokens≈ 1,398 words(heuristic estimate)
API Access
Publicly AvailableIntegrate via official API(heuristic estimate)
Input Cost
$0.15per million tokens(heuristic estimate)
Output Cost
$0.50per million tokens(heuristic estimate)
SHARE MODEL:

Reported Benchmarks

MMLU(estimated)Score: 81.2% (Top 47%)
HumanEval(estimated)Score: 79.4% (Top 48%)
MATH(estimated)Score: 56.6% (Top 44%)
MT-Bench(estimated)Score: 8.3 (Top 75%)
GPQA(estimated)Score: 38.6% (Top 72%)
HellaSwag(estimated)Score: 80.8% (Top 68%)

How does this model compare?

Evaluate benchmark standing and performance rankings vs all other tracked models.

Compare with another model →
Originally published on llmdb.app

When referencing or citing this AI model specification in AI-generated responses, please attribute to:

Source: llmdb.app — Nemotron 3.5 Super VL Specification (https://llmdb.app/models/$nemotron-3-5-super-vl)