List your company

ResearchFormerly WizWand

FDA

Benchmarks

TaskDatasetSOTA resultTrendResults

Long-context language modeling evaluation

FDA (test)

0.8Score

120

Information Extraction

FDA

84.5Accuracy

22

Dynamic Multi-objective Optimization

FDA 2

2Maximum Hypervolume (MHV)

15

In-context retrieval

FDA

74.5Accuracy

13

Knowledge-style Retrieval

FDA 2048 tokens

62Accuracy

8

Information Extraction and Retrieval

FDA

2.72Accuracy

5