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/Amazon
Amazon

Amazon · Nova 2

Amazon Nova 2 Omni (Preview)

Closed weightsPreviewproprietary

Preview any-to-text/image Nova model; Amazon has reportedly moved it to maintenance-only development.

AA Intelligence
13.6#81 of 142
Input / output per 1M
$0.30/ $2.50
Output speed
—
Context window
1M tokens

Composite indexes

  • Artificial Analysis Intelligence Index#81 of 142
    14independentIntelligence Index v4.3; medium reasoning; estimatedArtificial Analysis: Nova 2.0 Omni (medium) ↗

    Leader: Claude Opus 5.5 at 58

Coding

  • LiveCodeBench#29 of 56
    66%independentmedium reasoningArtificial Analysis: Nova 2.0 Omni (medium) ↗

    Leader: Fugu at 92.9%

Agents and tool use

  • τ²-Bench#32 of 88
    80.4%independenttelecom; medium reasoningArtificial Analysis: Nova 2.0 Omni (medium) ↗

    Leader: GLM-5.2 at 99.1%

Reasoning and knowledge

  • GPQA Diamond#84 of 142
    76%independentmedium reasoningArtificial Analysis: Nova 2.0 Omni (medium) ↗

    Leader: GPT-6 Astra at 96.1%

  • Humanity’s Last Exam#110 of 147
    7%independentno tools; medium reasoningArtificial Analysis: Nova 2.0 Omni (medium) ↗

    Leader: Claude Opus 5.5 at 61.4%

  • CritPt#116 of 139
    0%independentmedium reasoningArtificial Analysis: Nova 2.0 Omni (medium) ↗

    Leader: GPT-5.6 Sol at 32.3%

Vision and long context

  • AA Long Context Reasoning#86 of 139
    59.7%independentmedium reasoningArtificial Analysis: Nova 2.0 Omni (medium) ↗

    Leader: Kimi K3 at 88.7%

  • MMMU-Pro#57 of 72
    61.9%independentmedium reasoningArtificial Analysis: Nova 2.0 Omni (medium) ↗

    Leader: Claude Opus 5.5 at 87.7%

Other published results

ResultScoreReported bySource
aime-2025 · AIME 2025; medium reasoning89.7%independentArtificial Analysis: Nova 2.0 Omni (medium) ↗
Terminal-Bench Hard (AA) · medium reasoning4.5%independentArtificial Analysis: Nova 2.0 Omni (medium) ↗
IFBench · medium reasoning66.2%independentArtificial Analysis: Nova 2.0 Omni (medium) ↗
AA-Omniscience Index · medium reasoning-59.1 indexindependentArtificial Analysis: Nova 2.0 Omni (medium) ↗

Specs

Released
November 26, 2025
Parameters
Undisclosed
Size class
Undisclosed
Input
text, image, video, audio
Output
text, image
Context
1M tokens
Max output
Not published
Blended 70/30
$0.96 / 1M
  • Price: Amazon Nova pricing (Bedrock) ↗ Bedrock global cross-Region inference, Standard tier, text tokens; image output billed separately. Preview; reported in July 2026 to be in keep-the-lights-on mode.

Will it fit your budget?

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

Plan a stack →

Compare with

  • AmazonAmazon Nova 2 Lite13.4
  • ServiceNowApriel v1.6 15B Thinker13.4
  • CohereCommand A+13.1
  • GoogleGemma 4 12B14.2