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

Long-context Question Answering on NarrativeQA Passage Split

32.64Score

Baseline

15.89620.24324.5928.937Mar 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
32.64
2026.03
32.43
2026.03
31.81
2026.03
31.8
2026.03
31.79
2026.03
31.42
2026.03
31.41
2026.03
31.02
2026.03
31
2026.03
30.95
2026.03
28.1
2026.03
23.1
2026.03
22.91
2026.03
22.88
2026.03
21.97
2026.03
20.78
2026.03
18.62
2026.03
16.54