Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Question Answering on TriviaQA (EM, F1, SD, SE)

65.8EM

AutoSearch

12.44826.29940.1554.001Apr 19, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
65.873.11.0463.3
2026.04
63.771.41.8634.2
2026.04
61.7691.0558.7
2026.04
6168.41.7435
2026.04
55.865.20.9757.8
2026.04
54.763.31.7331.6
2026.04
52.460.31.6232.3
2026.04
51.659.91.9925.9
2026.04
51.3591.2939.9
2026.04
51.159.31.5732.7
2026.04
47.3552.916.3
2026.04
23.434.11.614.6
2026.04
14.524.21.3211