nvidia · Open weights
Nvidia Nemotron 3.5 Super VL
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 465 models
Side by side
Compare models
Put Nvidia Nemotron 3.5 Super VL next to up to three other models. The comparison stays in the link, so you can share it.
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
Intelligence Index
26.5
Better than 66% of 326 scored models
Agentic work
AutomationBench-AA
14.8%Workflow automation, penalized for guardrail violations
Better than 37% of 173 scored models
AutomationBench-AA tasks completed
2.0%Workflows finished end to end without a guardrail violation
Better than 35% of 173 scored models
AA-Briefcasev1.1
999 EloAgentic knowledge work, rated head to head
Better than 46% of 166 scored models
GDPval-AAv2.1
1,162 EloEconomically valuable occupational tasks, rated head to head
Better than 51% of 187 scored models
Document reasoning
GDP.pdf
8.0%Professional reasoning over PDF documents, all-pass rate
Better than 32% of 171 scored models
AA-LCRv1.1
69.0%Reasoning across long documents
Better than 45% of 309 scored models
MLCR-AA
13.3%Long-context reasoning over medical records
Better than 61% of 121 scored models
Reasoning and knowledge
Humanity’s Last Exam
30.7%Expert-level questions across academic fields
Better than 64% of 323 scored models
Coding
Terminal-Benchv4.0
0.0%Practical software engineering in a terminal
Better than 0% of 171 scored models
SciCode
47.8%Scientific computing in Python
Better than 41% of 174 scored models
Legacy evaluations
AA-LCR (unversioned)
69.0%Long-context reasoning, earlier grading
Better than 45% of 309 scored models
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 250 models
- Time to first token
- 1.8 s
- Quicker than 83% of 250 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.
- 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.
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
Related models
Other nvidia models, starting with the same family.