MultiExpertQA
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
MultiExpertQA All Base and Fine-tuned (FT)
79Accuracy
43
MultiExpertQA-P Base and Fine-tuned (FT)
85Accuracy
42
MultiExpertQA All (test)
0.79F1 Score
4
MultiExpertQA All
78F1 Score
3