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

Question Answering on TriviaQA (EM, ROUGE, F1)

65.7EM

GPT-4o

45.4250.68555.9561.215Apr 13, 2026
Updated 5d ago

Evaluation Results

MethodLinks
2026.04
65.764.378.2
2026.04
57.955.967.4
2026.04
5755.266.8
2026.04
5653.364.9
2026.04
55.657.869.7
2026.04
55.353.664.6
2026.04
53.650.961.9
2026.04
52.952.163
2026.04
51.352.262.5
2026.04
50.847.858.1
2026.04
50.349.159.2
2026.04
50.247.357.5
2026.04
50.124.857.2
2026.04
48.847.757.9
2026.04
48.648.556.4
2026.04
46.44756.8
2026.04
46.245.355.1