Amazon Nova Pro is a highly-capable multimodal model with state-of-the-art performance across text, image, and video understanding. It excels at core capabilities like language understanding, mathematical reasoning, and multimodal tasks while offering industry-leading speed and cost efficiency.
发布日期2024年11月20日
参数规模—
上下文长度—
许可证Proprietary
知识截止—
Benchmarks
评测成绩
| 评测基准 | 类别 | 分数 | 来源 |
|---|---|---|---|
| ARC-C | reasoning general | 94.8 | 来源 |
| GSM8k | math reasoning | 94.8 | 来源 |
| DocVQA | vision multimodal | 93.5 | 来源 |
| IFEval | general | 92.1 | 来源 |
| ChartQA | reasoning vision multimodal | 89.2 | 来源 |
| Translation en→Set1 COMET22 | language | 89.1 | 来源 |
| Translation Set1→en COMET22 | language | 89.0 | 来源 |
| HumanEval | reasoning code | 89.0 | 来源 |
| BBH | reasoning math language | 86.9 | 来源 |
| MMLU | general reasoning language math | 85.9 | 来源 |
| DROP | reasoning math | 85.4 | 来源 |
| TextVQA | vision multimodal image-to-text | 81.5 | 来源 |
| GroundUI-1K | multimodal vision | 81.4 | 来源 |
| VisualWebBench | vision multimodal frontend_development | 79.7 | 来源 |
| VATEX | multimodal video language | 77.8 | 来源 |
| FinQA | finance math reasoning | 77.2 | 来源 |
| MATH | math reasoning | 76.6 | 来源 |
| EgoSchema | vision reasoning long_context | 72.1 | 来源 |
| BFCL | general reasoning | 68.4 | 来源 |
| MM-Mind2Web | multimodal frontend_development reasoning | 63.7 | 来源 |
| MMMU | multimodal reasoning general | 61.7 | 来源 |
| CRAG | reasoning search | 50.3 | 来源 |
| GPQA | reasoning general | 46.9 | 来源 |
| Translation Set1→en spBleu | language | 44.4 | 来源 |
| Translation en→Set1 spBleu | language | 43.4 | 来源 |
| LVBench | vision multimodal long_context | 41.6 | 来源 |
| SQuALITY | summarization long_context language | 19.8 | 来源 |
Pricing
API 价格对比
暂无 API 价格。