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

Zero-shot long-context reasoning on ZeroSCROLLS

33.5Average Score

LLMLingua-2

11.97217.56123.1528.739Mar 20, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.03
33.53,20633.53.5
2026.03
33.41,898534.1
2026.03
33.43,089334.1
2026.03
33.31,86252.64.7
2026.03
333,41238.21.5
2026.03
32.71,75365.22.3
2026.03
32.59,788-12.2-
2026.03
32.43,31932.94.2
2026.03
321,87852.54.9
2026.03
30.73,36637.41.7
2026.03
27.21,86254.82.5
2026.03
243,34035.92.1
2026.03
22.43,362311.71
2026.03
20.73,460354.20.2
2026.03
20.61,78459.91.2
2026.03
20.51,77364.13
2026.03
19.41,865547.50.3
2026.03
12.832306112.2