Skip to contentT/TTokens or Towers

Compare

LeaderboardEvery tracked model, ranked and priced side by sideBenchmarksWhat each test measures and who leads itPricesAPI, media, and hardware rates with a cost calculator

Plan

Stack plannerSix questions to a priced local and hosted stackShortlistOur picks for subscriptions, APIs, and hardwareEnterpriseSeat plans against self-hosting for a whole team

Build

HardwareGPUs and workstations, and which models they fitHostsWhere to rent open-weight inference, and for how muchHarnessesCoding agents and the models they drive

Lab

FindingsResults from our own evaluationsScanAudit a repo’s AI usage in the browserMethodWhere the numbers come from and how we check them
Data checked September 25, 2026
Data checked September 25, 2026
Plan a stack
T/TTokens or Towers

An independent guide to AI models, what they cost, and the hardware to run them. No account, no API key, no sponsors.

Compare

  • Leaderboard
  • Benchmarks
  • Prices

Plan

  • Stack planner
  • Shortlist
  • Enterprise

Build

  • Hardware
  • Hosts
  • Harnesses

Lab

  • Findings
  • Scan
  • Method
Data checked September 25, 2026 · Every number links to its sourceRSS · Source on GitHub
Leaderboard/NVIDIA
NVIDIA

NVIDIA · Nemotron 3

Nemotron 3 Nano 4B

Open weightsGenerally availableNVIDIA Nemotron Open Model License

Tiny dense Nemotron 3 model for on-device and edge use.

AA Intelligence
7.4#120 of 142
Price
Self-host
Output speed
—
Context window
262K tokens

Composite indexes

  • Artificial Analysis Intelligence Index#120 of 142
    7independentIntelligence Index v4.3; reasoning; estimatedArtificial Analysis: NVIDIA Nemotron 3 Nano 4B ↗

    Leader: Claude Opus 5.5 at 58

Coding

  • Terminal-Bench 2.x#99 of 103
    3.7%independentTerminal-Bench 2.1; reasoningArtificial Analysis: NVIDIA Nemotron 3 Nano 4B ↗

    Leader: Claude Fable 5.1 at 91.4%

Agents and tool use

  • τ²-Bench#55 of 88
    28.1%independenttelecom; reasoningArtificial Analysis: NVIDIA Nemotron 3 Nano 4B ↗

    Leader: GLM-5.2 at 99.1%

  • GDPval-AA#99 of 103
    -74independentreasoningArtificial Analysis: NVIDIA Nemotron 3 Nano 4B ↗

    Leader: Claude Opus 5.5 at 1846

Reasoning and knowledge

  • GPQA Diamond#124 of 142
    51.3%independentreasoningArtificial Analysis: NVIDIA Nemotron 3 Nano 4B ↗

    Leader: GPT-6 Astra at 96.1%

  • Humanity’s Last Exam#124 of 147
    4.9%independentno tools; reasoningArtificial Analysis: NVIDIA Nemotron 3 Nano 4B ↗

    Leader: Claude Opus 5.5 at 61.4%

  • CritPt#112 of 139
    0%independentreasoningArtificial Analysis: NVIDIA Nemotron 3 Nano 4B ↗

    Leader: GPT-5.6 Sol at 32.3%

Vision and long context

  • AA Long Context Reasoning#113 of 139
    21.7%independentreasoningArtificial Analysis: NVIDIA Nemotron 3 Nano 4B ↗

    Leader: Kimi K3 at 88.7%

Other published results

ResultScoreReported bySource
Terminal-Bench Hard (AA) · reasoning6.8%independentArtificial Analysis: NVIDIA Nemotron 3 Nano 4B ↗
IFBench · reasoning58.2%independentArtificial Analysis: NVIDIA Nemotron 3 Nano 4B ↗
AA-Omniscience Index · reasoning-70.5 indexindependentArtificial Analysis: NVIDIA Nemotron 3 Nano 4B ↗

Specs

Released
March 16, 2026
Parameters
4B
Size class
Under 10B
Input
text
Output
text
Context
262K tokens
Max output
Not published

    Will it fit your budget?

    The planner prices this model against local hardware and other APIs for your workload.

    Plan a stack →

    Compare with

    • BaiduERNIE 4.5 300B A47B7.5
    • Nous ResearchHermes 4 405B7.5
    • PerplexitySonar Pro (Sonar API)7.6
    • Liquid AILFM2.5-8B-A1B7.2