Nova 2.0 Omni (Low) — benchmark results
Provider: Amazon. Released 2025-08-01. Access: API.
Unified ELO 1604 ± 18, rank #489 of 1841 rated models, from 54 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA IFBench | 61.77 | Accuracy (%) | 73 |
| AA MMLU-Pro | 79.76 | Accuracy (%) | 65.4 |
| AA LiveCodeBench | 59.15 | Pass@1 (%) | 65.2 |
| AA-LCR | 51 | Score (self-reported) | 64.7 |
| AA Omniscience - Software Engineering (SWE) - Rust | 56 | Accuracy (%) | 63.5 |
| AA TAU-2 Bench | 67.84 | Accuracy (%) | 60.8 |
| AA Omniscience - Software Engineering (SWE) - JavaScript | 33.64 | Accuracy (%) | 58.6 |
| AA Long Context Reasoning | 51 | Accuracy (%) | 58.3 |
| AA Global-MMLU-Lite - Arabic | 84.5 | Accuracy (%) | 57.2 |
| AA Global-MMLU-Lite - Hindi | 83.25 | Accuracy (%) | 55.6 |
| AA Global-MMLU-Lite - Indonesian | 86 | Accuracy (%) | 53.8 |
| AA Global-MMLU-Lite - Bengali | 82.25 | Accuracy (%) | 53.4 |
Interactive version: theaggregate.ai/model?slug=nova-2-0-omni-low · How It Works · Data refreshed daily, snapshot 2026-07-25.