NOUMENOpen app
NOUMEN

nvidia · Open weights

Nvidia Nemotron 3 Super 120B Thinking

Added Mar 1, 2026Open weights

Compare models

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

Loading models…

Use in the app

Nvidia Nemotron 3 Super 120B with reasoning content enabled. Returns separate thinking content when requested.

  • Reasoning
Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.05
Output
$0.25

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
16.4K
Average output (7 days)
621 tokens
Longer than 57% of 468 models

Side by side

Nvidia Nemotron 3 Super 120B Thinking 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 Super 120B ThinkingnvidiaThis modelGPT 4.1OpenAIRemove
ProvidernvidiaOpenAI
Discovery tierOpen weightsFrontier
AddedMar 1, 2026Sep 10, 2025
Limits
Context window262.14K1.05MBest
Max output16.38K32.77KBest
Average output621 tokens29 tokens
Pricing, USD per 1M tokens
Input$0.05Best$2.00
Output$0.25Best$8.00
Cache read—$0.50
Performance
Request success (24h)100.0%100.0%
Benchmark indexes
Intelligence Index12.8Best12.7
Coding Index37.7—
Math Index—34.7
Capabilities
ReasoningYesNo
ToolsNoYes
VisionNoYes
Structured outputNoYes
PDF inputNoYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • Nvidia Nemotron 3 Super 120B Thinking
  • GPT 4.1

Intelligence Index

  • Nvidia Nemotron 3 Super 120B Thinking12.8
  • GPT 4.112.7

Nvidia Nemotron 3 Super 120B Thinking: Better than 29% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Nvidia Nemotron 3 Super 120B Thinking: 37.7
    • GPT 4.1: —

  • Math Index

    Composite of the math evaluations

    • Nvidia Nemotron 3 Super 120B Thinking: —
    • GPT 4.1: 34.7

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Nvidia Nemotron 3 Super 120B Thinking: 3.8%
    • GPT 4.1: —

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Nvidia Nemotron 3 Super 120B Thinking: 0.3%
    • GPT 4.1: —

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Nvidia Nemotron 3 Super 120B Thinking: 490 Elo
    • GPT 4.1: —

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Nvidia Nemotron 3 Super 120B Thinking: 2.6%
    • GPT 4.1: —

  • AA-LCRv1.1

    Reasoning across long documents

    • Nvidia Nemotron 3 Super 120B Thinking: 65.7%
    • GPT 4.1: 68.3%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Nvidia Nemotron 3 Super 120B Thinking: 20.8%Top
    • GPT 4.1: 4.2%

  • GPQA Diamond

    Graduate-level science questions

    • Nvidia Nemotron 3 Super 120B Thinking: 80.0%Top
    • GPT 4.1: 66.6%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Nvidia Nemotron 3 Super 120B Thinking: —
    • GPT 4.1: 80.6%

  • IFBench

    Following precise output instructions

    • Nvidia Nemotron 3 Super 120B Thinking: 71.5%Top
    • GPT 4.1: 43.0%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Nvidia Nemotron 3 Super 120B Thinking: 0.0%
    • GPT 4.1: —

  • SciCode

    Scientific computing in Python

    • Nvidia Nemotron 3 Super 120B Thinking: 36.2%
    • GPT 4.1: —

  • LiveCodeBench

    Recent competitive programming problems

    • Nvidia Nemotron 3 Super 120B Thinking: —
    • GPT 4.1: 45.7%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Nvidia Nemotron 3 Super 120B Thinking: —
    • GPT 4.1: 34.7%

  • AIME

    Competition mathematics

    • Nvidia Nemotron 3 Super 120B Thinking: —
    • GPT 4.1: 43.7%

  • MATH-500

    Competition math problems

    • Nvidia Nemotron 3 Super 120B Thinking: —
    • GPT 4.1: 91.3%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Nvidia Nemotron 3 Super 120B Thinking: 28.8%Top
    • GPT 4.1: 13.6%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Nvidia Nemotron 3 Super 120B Thinking: 67.8%Top
    • GPT 4.1: 47.1%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Nvidia Nemotron 3 Super 120B Thinking: 65.7%
    • GPT 4.1: 68.3%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.

Prompt cache hits
0.0%
Request success (24h)
100.0%
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 100.0%
  • 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-super-120b-a12b:thinking",
    "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-super-120b-a12b:thinking",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

nvidia

Other nvidia models, starting with the same family.