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 Cascade

Nemotron Cascade 2 30B A3B

Open weightsGenerally availableNVIDIA Open Model License

Research open-weight 30B/3B-active reasoning model from NVIDIA's Cascade RL line.

AA Intelligence
11.7#91 of 142
Price
Self-host
Output speed
—
Context window
1M tokens

Composite indexes

  • Artificial Analysis Intelligence Index#91 of 142
    12independentIntelligence Index v4.3; reasoning; estimatedArtificial Analysis: Nemotron Cascade 2 30B A3B ↗

    Leader: Claude Opus 5.5 at 58

Coding

  • Terminal-Bench 2.x#83 of 103
    20.6%independentTerminal-Bench 2.1; reasoningArtificial Analysis: Nemotron Cascade 2 30B A3B ↗

    Leader: Claude Fable 5.1 at 91.4%

Agents and tool use

  • τ²-Bench#44 of 88
    53.2%independenttelecom; reasoningArtificial Analysis: Nemotron Cascade 2 30B A3B ↗

    Leader: GLM-5.2 at 99.1%

  • GDPval-AA#89 of 103
    252independentreasoningArtificial Analysis: Nemotron Cascade 2 30B A3B ↗

    Leader: Claude Opus 5.5 at 1846

Reasoning and knowledge

  • GPQA Diamond#85 of 142
    75.8%independentreasoningArtificial Analysis: Nemotron Cascade 2 30B A3B ↗

    Leader: GPT-6 Astra at 96.1%

  • Humanity’s Last Exam#87 of 147
    12%independentno tools; reasoningArtificial Analysis: Nemotron Cascade 2 30B A3B ↗

    Leader: Claude Opus 5.5 at 61.4%

  • CritPt#76 of 139
    0.6%independentreasoningArtificial Analysis: Nemotron Cascade 2 30B A3B ↗

    Leader: GPT-5.6 Sol at 32.3%

Vision and long context

  • AA Long Context Reasoning#97 of 139
    39.3%independentreasoningArtificial Analysis: Nemotron Cascade 2 30B A3B ↗

    Leader: Kimi K3 at 88.7%

Other published results

ResultScoreReported bySource
Terminal-Bench Hard (AA) · reasoning21.2%independentArtificial Analysis: Nemotron Cascade 2 30B A3B ↗
IFBench · reasoning80.4%independentArtificial Analysis: Nemotron Cascade 2 30B A3B ↗
AA-Omniscience Index · reasoning-51.5 indexindependentArtificial Analysis: Nemotron Cascade 2 30B A3B ↗

Specs

Released
March 19, 2026
Parameters
30B total, 3B active
Size class
10 to 40B
Input
text
Output
text
Context
1M 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

    • OpenAIgpt-oss-120b11.6
    • MistralMagistral Medium 1.211.8
    • PerplexitySonar Reasoning Pro (Sonar API)11.8
    • MeituanLongCat Flash Lite11.5