Nova Micro
Zero-eval
#3Translation Set1→en COMET22
#3Translation en→Set1 COMET22
#3FinQA
+3 more
by Amazon
+
+
+
+
About
Nova Micro is a language model developed by Amazon. It achieves strong performance with an average score of 67.0% across 17 benchmarks. It excels particularly in GSM8k (92.3%), ARC-C (90.2%), Translation Set1→en COMET22 (88.7%). It supports a 256K token context window for handling large documents. The model is available through 1 API provider. Released in 2024, it represents Amazon's latest advancement in AI technology.
+
+
+
+
Pricing Range
Input (per 1M)$0.03 -$0.03
Output (per 1M)$0.14 -$0.14
Providers1
+
+
+
+
Timeline
AnnouncedNov 20, 2024
ReleasedNov 20, 2024
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown
Overall Performance
17 benchmarks
Average Score
67.0%
Best Score
92.3%
High Performers (80%+)
6Performance Metrics
Max Context Window
256.0KAvg Throughput
100.0 tok/sAvg Latency
1ms+
+
+
+
All Benchmark Results for Nova Micro
Complete list of benchmark scores with detailed information
| GSM8k | text | 0.92 | 92.3% | Self-reported | |
| ARC-C | text | 0.90 | 90.2% | Self-reported | |
| Translation Set1→en COMET22 | text | 0.89 | 88.7% | Self-reported | |
| Translation en→Set1 COMET22 | text | 0.89 | 88.5% | Self-reported | |
| IFEval | text | 0.87 | 87.2% | Self-reported | |
| HumanEval | text | 0.81 | 81.1% | Self-reported | |
| BBH | text | 0.80 | 79.5% | Self-reported | |
| DROP | text | 0.79 | 79.3% | Self-reported | |
| MMLU | text | 0.78 | 77.6% | Self-reported | |
| MATH | text | 0.69 | 69.3% | Self-reported |
Showing 1 to 10 of 17 benchmarks