EXPERTQA
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
ExpertQA
61.1Balanced Accuracy
25
ExpertQA
23.34ROUGE-L
18
ExpertQA
33.55Snippet-F1
9
ExpertQA v1 (test)
0.661AutoAIS
9
ExpertQA
0.239Reward
8
EXPERTQA (test)
19.27Claim Recall
6
ExpertQA
73.9Faithfulness
5
ExpertQA Biomed
3.7Relevance
4
ExpertQA
7,985Total URLs
3