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

Long narrative understanding QA on NoCha

65.1Pair Accuracy

MiA-RAG

8.950423.527738.10552.6823Dec 19, 2025Jan 11, 2026Feb 3, 2026Feb 26, 2026Mar 21, 2026Apr 13, 2026May 7, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.05
65.182.5
2026.05
61.981
2026.05
58.779.4
2025.12
55.56-
2025.12
53.97-
2025.12
52.38-
2025.12
50.79-
2025.12
49.21-
2025.12
49.21-
2025.12
49.21-
2026.05
49.274.6
2025.12
47.62-
2026.05
47.671.4
2025.12
44.44-
2025.12
44.44-
2025.12
42.86-
2025.12
42.86-
2025.12
42.86-
2025.12
41.27-
2025.12
41.27-
2025.12
38.1-
2025.12
38.1-
2025.12
36.51-
2025.12
33.33-
2026.05
31.864.3
2025.12
31.75-
2025.12
30.16-
2025.12
28.57-
2025.12
26.98-
2025.12
26.98-
2025.12
26.98-
2025.12
22.22-
2025.12
19.05-
2025.12
17.46-
2025.12
17.46-
2025.12
15.87-
2025.12
15.87-
2025.12
11.11-
2025.12
-67.46
2025.12
-70.63
2025.12
-71.43
2025.12
-72.22
2025.12
-67.46
2025.12
-63.49
2025.12
-73.81
2025.12
-64.29
2025.12
-62.7
2025.12
-59.52
2025.12
-68.25
2025.12
-66.4
2025.12
-57.6
2025.12
-70.63