Nova Pro
Multimodal
Zero-eval
#1Translation en→Set1 COMET22
#1Translation Set1→en COMET22
#1GroundUI-1K
+9 more
by Amazon
+
+
+
+
About
Nova Pro is a multimodal language model developed by Amazon. It achieves strong performance with an average score of 73.2% across 27 benchmarks. It excels particularly in ARC-C (94.8%), GSM8k (94.8%), DocVQA (93.5%). It supports a 600K token context window for handling large documents. The model is available through 1 API provider. As a multimodal model, it can process and understand text, images, and other input formats seamlessly. Released in 2024, it represents Amazon's latest advancement in AI technology.
+
+
+
+
Pricing Range
Input (per 1M)$0.80 -$0.80
Output (per 1M)$3.20 -$3.20
Providers1
+
+
+
+
Timeline
AnnouncedNov 20, 2024
ReleasedNov 20, 2024
+
+
+
+
Specifications
Capabilities
Multimodal
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown
Overall Performance
27 benchmarks
Average Score
73.2%
Best Score
94.8%
High Performers (80%+)
13Performance Metrics
Max Context Window
600.0KAvg Throughput
100.0 tok/sAvg Latency
1ms+
+
+
+
All Benchmark Results for Nova Pro
Complete list of benchmark scores with detailed information
| ARC-C | text | 0.95 | 94.8% | Self-reported | |
| GSM8k | text | 0.95 | 94.8% | Self-reported | |
| DocVQA | multimodal | 0.94 | 93.5% | Self-reported | |
| IFEval | text | 0.92 | 92.1% | Self-reported | |
| ChartQA | multimodal | 0.89 | 89.2% | Self-reported | |
| Translation en→Set1 COMET22 | text | 0.89 | 89.1% | Self-reported | |
| HumanEval | text | 0.89 | 89.0% | Self-reported | |
| Translation Set1→en COMET22 | text | 0.89 | 89.0% | Self-reported | |
| BBH | text | 0.87 | 86.9% | Self-reported | |
| MMLU | text | 0.86 | 85.9% | Self-reported |
Showing 1 to 10 of 27 benchmarks