NOUMENOpen app
NOUMEN

nvidia · Open weights

Nvidia Nemotron 3.5 Super VL

Added Oct 15, 2026Open weights

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

NVIDIA’s open-weight 120B model (12B active) for reasoning, coding, tool use, document and GUI understanding, and video understanding. Text, images and video in; text out. A 262,144-token shared context window with responses limited to 16,384 tokens. OpenMDW 1.1 license.

  • Reasoning
  • Tools
  • Vision
  • Structured output
  • Video input
Input
Text, Images, Video
Output
Text
Reasoning effort
none · medium · high
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.15
Output
$0.50
Cache read
$0.02

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
16.4K
Average output (7 days)
1.1K tokens
Longer than 73% of 468 models

Side by side

Nvidia Nemotron 3.5 Super VL compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Nvidia Nemotron 3.5 Super VLnvidiaThis modelSolar Pro 4upstageRemove
Providernvidiaupstage
Discovery tierOpen weightsEfficient
AddedOct 15, 2026Aug 11, 2026
Limits
Context window262.14K524.29KBest
Max output16.38K131.07KBest
Average output1.1K tokens546 tokens
Pricing, USD per 1M tokens
Input$0.15$0.03Best
Output$0.50$0.12Best
Cache read$0.02$0.006Best
Performance
Throughput654.7 tok/sBest100.1 tok/s
Time to first token1.8 sBest3.1 s
Request success (24h)98.0%99.9%Best
Benchmark indexes
Intelligence Index26.526.6Best
Capabilities
ReasoningYesNo
ToolsYesYes
VisionYesNo
Structured outputYesYes
Video inputYesNo
Reasoning effortnone, medium, high—

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • Nvidia Nemotron 3.5 Super VL
  • Solar Pro 4

Intelligence Index

  • Nvidia Nemotron 3.5 Super VL26.5
  • Solar Pro 426.6

Nvidia Nemotron 3.5 Super VL: Better than 66% of 326 scored models

3.8Catalog models by score55.1

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Nvidia Nemotron 3.5 Super VL: 14.8%Top
    • Solar Pro 4: 13.6%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Nvidia Nemotron 3.5 Super VL: 2.0%
    • Solar Pro 4: 2.4%Top

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Nvidia Nemotron 3.5 Super VL: 999 Elo
    • Solar Pro 4: 1,093 EloTop

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Nvidia Nemotron 3.5 Super VL: 1,162 EloTop
    • Solar Pro 4: 1,106 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Nvidia Nemotron 3.5 Super VL: 8.0%Top
    • Solar Pro 4: 7.0%

  • AA-LCRv1.1

    Reasoning across long documents

    • Nvidia Nemotron 3.5 Super VL: 69.0%
    • Solar Pro 4: 70.7%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • Nvidia Nemotron 3.5 Super VL: 13.3%
    • Solar Pro 4: —

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Nvidia Nemotron 3.5 Super VL: 30.7%Top
    • Solar Pro 4: 29.8%

  • GPQA Diamond

    Graduate-level science questions

    • Nvidia Nemotron 3.5 Super VL: —
    • Solar Pro 4: 89.1%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Nvidia Nemotron 3.5 Super VL: 0.0%Top
    • Solar Pro 4: 0.0%Top

  • SciCode

    Scientific computing in Python

    • Nvidia Nemotron 3.5 Super VL: 47.8%
    • Solar Pro 4: 48.0%Top

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Nvidia Nemotron 3.5 Super VL: 69.0%
    • Solar Pro 4: 70.7%Top

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Throughput
654.7 tok/s
Faster than 98% of 254 models
Time to first token
1.8 s
Quicker than 85% of 254 models
Prompt cache hits
66.9%
About $0.063 per 1M input tokens with caching
Request success (24h)
98.0%
Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 72.8%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3.5-super-vl",
    "reasoning_effort": "medium",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="nvidia/nemotron-3.5-super-vl",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

nvidia

Other nvidia models, starting with the same family.