Nova 2.0 Lite (Low): benchmark results
Provider: Amazon. Released 2025-12-02. Access: API.
Unified ELO 1548 ± 1, rank #990 of 3078 rated models, from 41 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA IFBench | 61.22 | Accuracy (%) | 72.4 |
| Tau2-Bench Telecom | 71.93 | Success Rate (%) | 65.7 |
| AA TAU-2 Bench | 71.93 | Accuracy (%) | 64.1 |
| AA MMLU-Pro | 78.78 | Accuracy (%) | 61.5 |
| AA LiveCodeBench | 46.88 | Pass@1 (%) | 53.5 |
| Artificial Analysis Intelligence Index | 11.8 | Intelligence Index | 51.2 |
| AA Long Context Reasoning | 54.33 | Accuracy (%) | 50.1 |
| AA GPQA Diamond | 69.8 | Accuracy (%) | 47.7 |
| Sonar LLM Leaderboard - Java - Bug Density | 0.92 | Bugs per 1,000 lines of code (lower is better) | 47.2 |
| Sonar LLM Leaderboard - Java - Pass Rate | 76.26 | Passing tests (%) | 45.8 |
| AA AIME 2025 | 46.67 | Accuracy (%) | 45.6 |
| AA-Omniscience Index - Software Engineering (SWE) - HTML | -28 | Omniscience Index | 45.4 |
Interactive version: theaggregate.ai/model?slug=nova-2-0-lite-low · How It Works · Data refreshed daily, snapshot 2026-09-19.