Nova Pro: benchmark results
Amazon's mid-tier Nova multimodal model handling text, image and video input with a 300K context on Bedrock (December 2024). Provider: Amazon. Released 2024-12-03. Access: API.
Aggregate Rating 1564 ± 11, rank #569 of 1656 rated models, from 218 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM NaturalQuestions (Open) | 82.9 | F1 (%) | 100 |
| Translation en to Set1 spBleu | 43.4 | en→Set1 spBLEU (imported) | 100 |
| HELM Lite - LegalBench | 73.62 | Exact Match (%) | 96.7 |
| HELM Lite - WMT 2014 (ru-en) | 28.14 | BLEU-4 (%) | 96.7 |
| HELM (Stanford) | 88.48 | Mean Win Rate (%) | 95.6 |
| HELM MMLU - College Chemistry | 63 | EM | 95.5 |
| HELM MMLU - High School Physics | 74.17 | EM | 95.5 |
| HELM Lite - MATH Level 1 - Intermediate Algebra | 82.69 | Equivalent (CoT) (%) | 95 |
| HELM NarrativeQA | 79.13 | F1 (%) | 95 |
| HELM MMLU - Formal Logic | 71.43 | EM | 94.9 |
| HELM Lite - LegalBench - International Citizenship Questions | 65.5 | Exact Match (%) | 94.4 |
| HELM Lite - MATH Level 1 - Precalculus | 84.21 | Equivalent (CoT) (%) | 94.4 |
Interactive version: theaggregate.ai/model?slug=nova-pro · How It Works · Data refreshed daily, snapshot 2026-10-20.