FDA
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Long-context language modeling evaluation | FDA (test) | Score0.8004 | 120 | |
| Information Extraction | FDA | Accuracy84.5 | 22 | |
| Dynamic Multi-objective Optimization | FDA 2 | Maximum Hypervolume (MHV)2 | 15 | |
| In-context retrieval | FDA | Accuracy74.5 | 13 | |
| Knowledge-style Retrieval | FDA 2048 tokens | Accuracy62 | 8 | |
| Information Extraction and Retrieval | FDA | Accuracy2.72 | 5 |
Showing 6 of 6 rows