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

Humor generation on SemEval Task 1 2026 (test)

1,323.7BT Rating

GPT-5

578.436771.918965.41,158.882Mar 19, 2026
Updated 5d ago

Evaluation Results

MethodLinks
2026.03
1,323.71,28884.7
2026.03
1,221.61,18875.3
1,190.31,15772
2026.03
1,083.91,05759.5
2026.03
1,079.91,05559
2026.03
1,034.51,00153.3
2026.03
993.296548.2
2026.03
989.295747.7
2026.03
975.895046
2026.03
964.393644.5
2026.03
883.584835
2026.03
653.161013.8
2026.03
607.156010.8