Nova Premier (v1): benchmark results
Provider: Amazon. Released 2025-04-30. Access: API.
Aggregate Rating 1581 ± 25, rank #1242 of 10916 rated models, from 170 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| IKP - T1 | 100 | Accuracy (%) | 86.1 |
| Evals for Every Language - Sanskrit (sa) | 67.28 | Average Score (%) | 81 |
| Evals for Every Language - Arabic (ar) | 68.56 | Average Score (%) | 76.9 |
| Evals for Every Language - Classification | 91.39 | Average Score (%) | 76.5 |
| Evals for Every Language - Urdu (ur) | 71.36 | Average Score (%) | 75.4 |
| Evals for Every Language - Nepali (ne) | 69.67 | Average Score (%) | 73.4 |
| Evals for Every Language - Yiddish (yi) | 70.72 | Average Score (%) | 72.7 |
| Evals for Every Language - Shan (shn) | 38.64 | Average Score (%) | 71.2 |
| Evals for Every Language - Thai (th) | 75.95 | Average Score (%) | 69.7 |
| Evals for Every Language - Tajik (tg) | 69.36 | Average Score (%) | 67.7 |
| Evals for Every Language - Kurdish (ku) | 65.97 | Average Score (%) | 67.2 |
| Evals for Every Language - Persian (fa) | 71.98 | Average Score (%) | 66.2 |
Interactive version: theaggregate.ai/model?slug=nova-premier-v1 · How It Works · Data refreshed daily, snapshot 2026-11-08.