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

Question Answering on OpenBookQA (Accuracy and Token Count)

95.2Accuracy

ART-max

27.645.1562.780.25Jul 21, 2025Sep 3, 2025Oct 18, 2025Dec 1, 2025Jan 15, 2026Feb 28, 2026Apr 14, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.04
95.2-
2026.04
95.1-
2026.04
95-
2026.04
93-
2026.04
93-
2026.04
92.8-
2026.04
87.6-
2026.04
87.2-
2026.04
87.2-
2026.04
85.4-
2026.04
85.2-
2026.04
85.1-
2026.02
84.83428
2026.04
84.8-
2026.04
84.6-
2026.04
84.4-
2026.04
84.3-
2026.04
84.3-
2026.02
84.17448
2026.04
84.1-
2026.02
80.5459
2026.02
73.83388
2026.02
73.67534
2026.02
67.83621
2026.02
64.33490
2026.04
51.2-
2026.04
50.8-
2026.04
49.6-
2026.04
49-
2026.04
45.9-
2026.04
45.6-
2026.04
45.2-
2026.04
44.9-
2026.04
44.8-
2026.02
44.17451
2026.02
42.5655
2026.02
42.17553
2025.07
42.14-
2026.02
41563
2026.02
40.83566
2025.07
40.7-
2026.04
39.8-
2025.07
39.8-
2026.02
39.17471
2025.07
39.04-
2025.07
38.8-
2025.07
38.28-
2025.07
37.8-
2025.07
37.6-
2026.02
37.33643
2026.03
37.2-
2025.07
37-
2025.07
36.6-
2025.07
36.45-
2026.03
36.4-
2026.02
36.33550
2026.03
36-
2025.07
35.9-
2026.04
35.8-
2026.04
35.8-
2026.03
35.2-
2026.04
35.2-
2026.04
35.2-
2026.03
35-
2026.04
35-
2025.07
35-
2026.03
34.2-
2025.07
34.2-
2026.03
34-
2025.07
34-
2026.03
33.8-
2026.03
33.8-
2026.04
33.8-
2026.03
33.6-
2026.03
33.6-
2026.03
33.6-
2025.07
33.4-
2026.03
33.2-
2026.03
33.2-
2026.04
33.2-
2026.04
33.2-
2025.07
33.2-
2026.03
33-
2026.04
32.8-
2026.04
32.4-
2026.04
32.2-
2026.04
32.2-
2026.03
32-
2026.04
32-
2026.04
32-
2026.03
31.8-
2026.03
31.6-
2026.03
31.4-
2026.04
31.4-
2026.03
31.2-
2026.04
31.2-
2026.04
31.1-
2026.03
30.6-
2025.07
30.6-
2026.03
30.2-
Showing 100 of 119 rows