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

Long-context Question Answering on HotpotQA 128K

25Accuracy

RECONTEXT

-15.7512.519.25Jul 2, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.07
2539
2026.07
2439
2026.07
2434
2026.07
2339
2026.07
2337
2026.07
2235
2026.07
2132
2026.07
2034
2026.07
1931
2026.07
1831
2026.07
1831
2026.07
1630
2026.07
819
2026.07
717
2026.07
615
2026.07
313
2026.07
010
2026.07
09