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 30B A3B

Open weightsGenerally availableNVIDIA Nemotron Open Model License

Original small Nemotron 3 hybrid MoE; effectively superseded by Nemotron 3.5 Lightning at the same size.

AA Intelligence
8.9#107 of 142
Input / output per 1M
$0.05/ $0.20
Output speed
195tok/s
Context window
1M tokens

Composite indexes

  • Artificial Analysis Intelligence Index#107 of 142
    9independentIntelligence Index v4.3; reasoningArtificial Analysis: NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) ↗

    Leader: Claude Opus 5.5 at 58

Coding

  • SciCode#88 of 94
    30.6%independentreasoningArtificial Analysis: NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) ↗

    Leader: Claude Opus 5.5 at 66.9%

  • Terminal-Bench 4.0#83 of 88
    0%independentreasoningArtificial Analysis: NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) ↗

    Leader: Claude Mythos 5.1 at 60.9%

  • Terminal-Bench 2.x#95 of 103
    6.7%independentTerminal-Bench 2.1; reasoningArtificial Analysis: NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) ↗

    Leader: Claude Fable 5.1 at 91.4%

  • LiveCodeBench#18 of 56
    74.1%independentreasoningArtificial Analysis: NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) ↗

    Leader: Fugu at 92.9%

  • SWE-bench Verified#16 of 16
    34.1%vendorNVIDIA harnessNVIDIA Nemotron 3.5 Lightning model card (NVIDIA-measured comparison table) ↗

    Leader: Claude Sonnet 5 at 85.2%

Agents and tool use

  • τ²-Bench#51 of 88
    40.9%independenttelecom; reasoningArtificial Analysis: NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) ↗

    Leader: GLM-5.2 at 99.1%

  • GDPval-AA#90 of 103
    241independentreasoningArtificial Analysis: NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) ↗

    Leader: Claude Opus 5.5 at 1846

Reasoning and knowledge

  • GPQA Diamond#86 of 142
    75.7%independentreasoningArtificial Analysis: NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) ↗
    74.0%vendorno tools; NVIDIA harnessNVIDIA Nemotron 3.5 Lightning model card (NVIDIA-measured comparison table) ↗

    Leader: GPT-6 Astra at 96.1%

  • Humanity’s Last Exam#92 of 147
    11.4%independentno tools; reasoningArtificial Analysis: NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) ↗

    Leader: Claude Opus 5.5 at 61.4%

  • CritPt#72 of 139
    0.9%independentreasoningArtificial Analysis: NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) ↗

    Leader: GPT-5.6 Sol at 32.3%

  • MMLU-Pro#7 of 14
    78.5%vendorNVIDIA harnessNVIDIA Nemotron 3.5 Lightning model card (NVIDIA-measured comparison table) ↗

    Leader: Nemotron 3 Ultra 550B A55B at 86.8%

Vision and long context

  • AA Long Context Reasoning#98 of 139
    38%independentreasoningArtificial Analysis: NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) ↗

    Leader: Kimi K3 at 88.7%

Other published results

ResultScoreReported bySource
aime-2025 · AIME 2025; reasoning91%independentArtificial Analysis: NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) ↗
Terminal-Bench Hard (AA) · reasoning13.6%independentArtificial Analysis: NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) ↗
IFBench · reasoning71.1%independentArtificial Analysis: NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) ↗
tau2-Bench Banking (AA) · reasoning6%independentArtificial Analysis: NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) ↗
AA-Omniscience Index · reasoning-51.6 indexindependentArtificial Analysis: NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) ↗

Specs

Released
December 15, 2025
Parameters
30B total, 3B active
Size class
10 to 40B
Input
text
Output
text
Context
1M tokens
Max output
Not published
Cached input
$0.05 / 1M
Blended 70/30
$0.095 / 1M
First token
1.12s
  • Price: Artificial Analysis model page ↗ No first-party paid NVIDIA API (build.nvidia.com is a free trial endpoint). Value is the Artificial Analysis median across third-party API providers.
  • Speed: Artificial Analysis leaderboard (NVIDIA Nemotron 3 Nano 30B A3B (Reasoning), median across providers or first-party as shown) ↗

Will it fit your budget?

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

Plan a stack →

Compare with

  • GoogleGemma 4 E4B8.9
  • OpenAIgpt-oss-20b9
  • Sarvam AISarvam 105B8.8
  • IBMGranite 4.2 3B9.1