Amazon / MODEL EVIDENCE

Nova 2.0 Pro Preview

4 benchmarks · 6 observations · 4 sources

Scores at a glance

4 benchmarks · large dot: Nova 2.0 Pro Preview; small dots: closest models where reported

75.5883.33

Nova 2.0 Pro Preview (Low) · IFBench · AA implementation ↗

00

Nova 2.0 Pro Preview (medium) · CritPt · Accuracy · % ↗

1 more reported result

0% · Nova 2.0 Pro Preview (low) · CritPt · Accuracy · % · Epoch AI · CritPt ↗

42.7142.71

Nova 2.0 Pro Preview (medium) · SciCode · Score · % ↗

1 more reported result

38.66% · Nova 2.0 Pro Preview (low) · SciCode · Score · % · Epoch AI · SciCode ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

How similarity is measured

Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

  1. Global-MMLU-Lite Benchmark | Artificial Analysis ↗

    Artificial Analysis

  2. IFBench Benchmark | Artificial Analysis ↗

    Artificial Analysis

  3. SciCode Benchmark | Artificial Analysis ↗

    Artificial Analysis

  4. CritPt v1 ↗

    Epoch AI

Release dates reported by sources

2025-11-27 · 2025-12-02

Names used in source tables

Nova 2.0 Pro Preview (Low) · Nova 2.0 Pro Preview (low) · Nova 2.0 Pro Preview (medium)