Nova 2.0 Pro Preview (Non-reasoning): benchmark results
Provider: Amazon. Released 2025-12-02. Access: API.
Aggregate Rating 1543 ± 22, rank #908 of 2169 rated models, from 56 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Tau2-Bench Telecom | 71.64 | Success Rate (%) | 65.5 |
| AA TAU-2 Bench | 71.64 | Accuracy (%) | 64 |
| AA IFBench | 52.04 | Accuracy (%) | 62.4 |
| AA MMLU-Pro | 77.16 | Accuracy (%) | 55.2 |
| AA LiveCodeBench | 47.3 | Pass@1 (%) | 54.5 |
| AA Terminal-Bench Hard | 16.67 | Accuracy (%) | 54.2 |
| AA-Omniscience Hallucination Rate | 79.94 | Hallucination Rate (%) | 50.9 |
| AA Global-MMLU-Lite - Portuguese | 86.75 | Accuracy (%) | 50.5 |
| AA Global-MMLU-Lite - English | 89.75 | Accuracy (%) | 46.4 |
| AA-Omniscience Index - Software Engineering (SWE) - JavaScript | -29.09 | Omniscience Index | 43.8 |
| AA Global-MMLU-Lite - Yoruba | 51.5 | Accuracy (%) | 43.6 |
| Artificial Analysis Intelligence Index | 9.96 | Intelligence Index | 41.9 |
Interactive version: theaggregate.ai/model?slug=nova-2-0-pro-preview-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-23.