Benchmarks
More
OverviewBenchmaxxingCompareChartsCost vs CapabilityProviders per ModelProvider explorerGatewaysEU & SovereignJev-class modelsAbout
← All models

Nova 2.0 Pro Preview (low)

Amazon · released 2025-11-27 · 0 offers

Output 126 tokens/sFirst token 6.0 sContext 256K tokens

Providers

No provider publishes an API price for this model yet, so no cost can be modeled.

Composite

2 of 7 inputs6 radar axes: DesignArena's two boards share one

26.7

AA CodingCoding Agent v1.4AA IntelligenceAA AgenticEpoch ECISoftware ECIDesignArenaAA Coding: percentile 32AA Intelligence: percentile 55

AA Coding 25.9Coding Agent v1.4 —AA Intelligence 12.8AA Agentic —Epoch ECI —Software ECI —DesignArena —/—

Radar: percentile among all models measured on each input; a gap means not measured.

Benchmark sheet

12 of 201 registered benchmark versions · bars show the percentile among all models measured on each benchmark.

Compare this model →

Agentic

  • GDPval-AA v227601 Elo

    GDPval-AA v2 v2 ↗ · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.

  • Terminal-Bench Hard (AA)5617.4%

    Terminal-Bench Hard (AA) pinned revision 74221fb ↗ · Published board — Tests a pinned 44-task hard subset of terminal-based work using Terminus 2.

  • Terminal-Bench v2.1 (AA)2619.5%

    Terminal-Bench v2.1 (AA) v2.1 ↗ · Published board — Tests terminal-based work on the 89-task verified refresh using Terminus 2.

Coding

  • AA Coding Index3225.9

    AA Coding Index published 2026-09-20 ↗ · Published board — Artificial Analysis publishes this board without a version number; we keep the date each result was retained.

Instruction-following

Knowledge

Long-context

  • AA-LCR v1.16064.7%

    AA-LCR v1.1 v1.1 ↗ · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.

Math

  • AIME 2025 (AA) v20255963.3%

    AIME 2025 (AA) v2025 ↗ · Published board — Advanced mathematical problem solving on AIME I and II 2025.

Reasoning

Science

Tool-use

Vision

Unusual results

1 threshold-crossing signal flagged · 14 eligible benchmark families

How flags are calculated

Heuristic screen, not statistical significance: benchmark families are correlated and source uncertainty is unknown. Peer evidence needs ≥ 20 independently measured matched configurations from ≥ 10 distinct model families. A flag needs a directed population z-score of magnitude ≥ 1.5 and a gap of ≥ 1.5 from the leave-one-benchmark-family-out mean z in the same direction, over ≥ 5 other benchmark families.

  • unusually strong IFBench (AA single-turn) published 2026-09-10
    Why
    Observed: 0.79592 fraction
    Peer mean 0.48006 · peer sd 0.17139 · n 450 · families 331
    Directed z 1.843 · baseline z -0.132 · gap 1.975 · profile n 13
    0.79592 fractionmeasuredobserved 2026-09-10artificialanalysis.ai ↗
    Evidence
    Axis: IFBench (AA single-turn) · published 2026-09-10 · Published board
    Exact value: 0.795918367346939 fraction
    Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
    Observation id: aa:f4274721-ef28-4121-aa88-8e97267a5a82:ifbench
Missing coverage · 192 benchmark versions

No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.

Variants / reasoning settings

Artificial Analysis snapshot 2026-09-20 · Data: Artificial Analysis · Data: Epoch AI (CC BY)

VariantAA CodingAA Intelligence
Nova 2.0 Pro Preview (medium)34.014.2
Nova 2.0 Pro Preview (low)25.912.8
Nova 2.0 Pro Preview (Non-reasoning)20.910.0
Nova 2.0 Pro Preview (low) — benchmarks & cost | Benchmark Heaven