Nova 2.0 Lite (High): benchmark results
Provider: Amazon. Released 2025-12-02. Access: API.
Aggregate Rating 1576 ± 25, rank #811 of 2201 rated models, from 83 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA AIME 2025 | 94.33 | Accuracy (%) | 95.4 |
| Nejumi 4 - Toxicity - Prohibited Acts | 97.92 | Criteria met (%) | 93.8 |
| Nejumi 4 - MT-Bench (Japanese) - Humanities | 100 | Judge rating (1-10, x10) | 90.8 |
| Nejumi 4 - MT-Bench (Japanese) - STEM | 100 | Judge rating (1-10, x10) | 89.7 |
| Nejumi 4 - MT-Bench (Japanese) - Math | 100 | Judge rating (1-10, x10) | 89.4 |
| AA IFBench | 70.75 | Accuracy (%) | 85.7 |
| AA LiveCodeBench | 71.11 | Pass@1 (%) | 81.4 |
| AA MMLU-Pro | 81.82 | Accuracy (%) | 76.7 |
| Nejumi 4 - JBBQ (2-shot) - Accuracy | 92 | Accuracy (%) | 73.3 |
| Nejumi 4 - MT-Bench (Japanese) - Roleplay | 98 | Judge rating (1-10, x10) | 72.9 |
| AA GPQA Diamond | 81.11 | Accuracy (%) | 68.9 |
| Nejumi 4 - jaster (0-shot) - MAWPS | 98 | Exact match (%) | 68.2 |
Interactive version: theaggregate.ai/model?slug=nova-2-0-lite-high · How It Works · Data refreshed daily, snapshot 2026-11-12.