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

Multi-hop Question Answering on 2WikiMultiHopQA (test)

73.9EM

CJ

30.7441.94553.1564.355Dec 20, 2022Jul 22, 2023Feb 22, 2024Sep 23, 2024Apr 26, 2025Nov 26, 2025Jun 29, 2026
Updated 25d ago

Evaluation Results

MethodLinks
2026.04
73.9-------------
2026.04
73.6-------------
2026.04
71.8-------------
2026.06
69.8--76.2---76.4------
2026.06
69.8--76.3---77.3------
2026.06
67.6--73.4---72.9------
2026.04
66.8-------------
2026.04
65.3-------------
2026.06
64.8--71---71.1------
2025.12
64.6-------------
2026.06
64.2--72.4---74.6------
2026.06
64.2--73.3---75.3------
2026.06
63.8--69.7---69.6------
2026.02
63.3-------------
2026.04
62.9-------------
2026.01
62.8--72.2----------
2026.05
61.72--69.2----------
2026.04
61.7-------------
2026.06
60.9--68.3---67.6------
2026.04
60.6-------------
2025.08
60.2--72.7----------
2026.06
60.2--67.7---68.1------
2025.12
60-------------
2025.12
59.7-------------
2025.12
59.5-------------
2026.01
59.38--69.75----------
2026.05
58.59--68.18----------
2026.01
57.8--68.4----------
2022.12
57.7--68----------
2026.04
56.7-------------
2026.04
56-------------
2026.01
55.47--61.72----------
2026.01
55.47--65.04----------
2026.04
55.2-------------
2025.12
54.7-------------
2026.01
52.5--63.87----------
2026.01
52.02--63.68----------
2026.04
51.4-------------
2025.12
51-------------
2026.06
50.9--58.6----------
2026.06
50.2--55.57----------
2025.12
50.1-------------
2025.05
50--59.7----------
2026.01
50--60.26----------
2026.01
50--57.56----------
2025.12
50-------------
2025.12
49.8-------------
2025.05
49.7--54.9----------
2026.04
49.5-------------
2026.01
48.8--8.66---22------
2026.04
48.8-------------
2025.12
48.3-------------
2026.04
48.1-------------
2025.12
47.3-------------
2026.01
46.7--54.8----------
2026.06
45.7--51.17----------
2026.04
45.5-------------
2026.05
45.31--51.55----------
2025.05
44.6--52.2----------
2025.05
44.5--51.9---53.5------
2026.01
44.5--59.67----------
2026.04
44.4-------------
2026.06
44.4--48.49----------
2025.08
44.3--55.8----------
2025.08
43.3--56.2----------
2025.05
43.2--54.2----------
2025.12
42.9-------------
2026.02
42.8-------------
2025.08
42.3--50.7----------
2026.02
41.4-------------
2026.02
40.9-------------
2025.05
40.6--49.8----------
2022.12
40.1-------------
2026.02
39.3-------------
2026.01
38.5--54.94----------
2025.12
38.4-------------
2026.02
38-------------
2026.02
37.4-------------
2023.05
37.2----9.532.28-------
2026.01
36.72--41.29----------
2026.01
36.2--45.5----------
2026.02
36.1-------------
2025.12
35.9-------------
2026.04
35.8-------------
2026.05
35.15--38.21----------
2026.02
34.6-------------
2026.02
34.6-------------
2026.04
34-------------
2026.02
33.9-------------
2026.04
33.8-------------
2023.05
33.6----5.930.06-------
2025.12
33.5-------------
2026.04
33.5-------------
2026.01
33.4--15.78---23.2------
2023.05
33.1----5.428.32-------
2026.04
33.1-------------
2025.05
32.8--41.6----------
2026.01
32.8--37.3----------
2026.06
32.8--42.3---47.2------
2026.06
32.4--38.24----------
Showing 100 of 317 rows