NOUMENOpen app
NOUMEN

nvidia · Open weights

Nvidia Nemotron 3.5 Lightning TEE

Added Sep 11, 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 30B mixture-of-experts model with 3B active parameters for fast agentic workflows, coding, and tool use. Running inside a TEE (Trusted Execution Environment), with provider attestation support.

  • Reasoning
  • Tools
  • Structured output
Input
Text
Output
Text
Reasoning effort
none · low · medium · high
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.08
Output
$0.20
Cache read
$0.04

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
65.5K

Side by side

Nvidia Nemotron 3.5 Lightning TEE 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 Lightning TEEnvidiaThis modelNvidia Nemotron 3 Ultra 550B ThinkingnvidiaRemove
Providernvidianvidia
Discovery tierOpen weightsOpen weights
AddedSep 11, 2026Jun 4, 2026
Limits
Context window262.14K1MBest
Max output65.54K65.54K
Average output—654 tokens
Pricing, USD per 1M tokens
Input$0.08Best$0.50
Output$0.20Best$2.50
Cache read$0.04—
Performance
Throughput—79.0 tok/s
Time to first token—2.1 s
Request success (24h)—99.7%
Benchmark indexes
Intelligence Index12.922.9Best
Coding Index26.849.3Best
Capabilities
ReasoningYesYes
ToolsYesYes
Structured outputYesNo
Parallel toolsNoYes
Reasoning effortnone, low, medium, high—

Public evaluations

Benchmarks

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

  • Nvidia Nemotron 3.5 Lightning TEE
  • Nvidia Nemotron 3 Ultra 550B Thinking

Intelligence Index

  • Nvidia Nemotron 3.5 Lightning TEE12.9
  • Nvidia Nemotron 3 Ultra 550B Thinking22.9

Nvidia Nemotron 3.5 Lightning TEE: Better than 30% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Nvidia Nemotron 3.5 Lightning TEE: 26.8
    • Nvidia Nemotron 3 Ultra 550B Thinking: 49.3Top

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Nvidia Nemotron 3.5 Lightning TEE: 0.8%
    • Nvidia Nemotron 3 Ultra 550B Thinking: 3.0%Top

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Nvidia Nemotron 3.5 Lightning TEE: 0.0%
    • Nvidia Nemotron 3 Ultra 550B Thinking: 0.3%Top

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Nvidia Nemotron 3.5 Lightning TEE: 506 Elo
    • Nvidia Nemotron 3 Ultra 550B Thinking: 876 EloTop

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Nvidia Nemotron 3.5 Lightning TEE: 638 Elo
    • Nvidia Nemotron 3 Ultra 550B Thinking: 1,013 EloTop

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Nvidia Nemotron 3.5 Lightning TEE: 3.0%
    • Nvidia Nemotron 3 Ultra 550B Thinking: 5.0%Top

  • AA-LCRv1.1

    Reasoning across long documents

    • Nvidia Nemotron 3.5 Lightning TEE: 60.3%
    • Nvidia Nemotron 3 Ultra 550B Thinking: 79.3%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • Nvidia Nemotron 3.5 Lightning TEE: 2.2%
    • Nvidia Nemotron 3 Ultra 550B Thinking: 5.6%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Nvidia Nemotron 3.5 Lightning TEE: 10.6%
    • Nvidia Nemotron 3 Ultra 550B Thinking: 28.4%Top

  • GPQA Diamond

    Graduate-level science questions

    • Nvidia Nemotron 3.5 Lightning TEE: 74.3%
    • Nvidia Nemotron 3 Ultra 550B Thinking: 86.7%Top

  • IFBench

    Following precise output instructions

    • Nvidia Nemotron 3.5 Lightning TEE: —
    • Nvidia Nemotron 3 Ultra 550B Thinking: 81.4%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Nvidia Nemotron 3.5 Lightning TEE: 0.5%Top
    • Nvidia Nemotron 3 Ultra 550B Thinking: 0.5%Top

  • SciCode

    Scientific computing in Python

    • Nvidia Nemotron 3.5 Lightning TEE: 32.1%
    • Nvidia Nemotron 3 Ultra 550B Thinking: 40.3%Top

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Nvidia Nemotron 3.5 Lightning TEE: —
    • Nvidia Nemotron 3 Ultra 550B Thinking: 36.4%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Nvidia Nemotron 3.5 Lightning TEE: —
    • Nvidia Nemotron 3 Ultra 550B Thinking: 83.3%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Nvidia Nemotron 3.5 Lightning TEE: 60.3%
    • Nvidia Nemotron 3 Ultra 550B Thinking: 79.3%Top

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

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": "TEE/nemotron-3.5-lightning",
    "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="TEE/nemotron-3.5-lightning",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

nvidia

Other nvidia models, starting with the same family.