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

Question Answering on Eight QA datasets Average

65.2Accuracy

FP Model

30.3639.40548.4557.495May 17, 2026
Updated 15d ago

Evaluation Results

MethodLinks
2026.05
65.2
2026.05
58.7
2026.05
58.6
2026.05
58.6
2026.05
58.5
2026.05
57.8
2026.05
57.2
2026.05
56.7
2026.05
56.6
2026.05
56.5
2026.05
56.4
2026.05
55.9
2026.05
55.6
2026.05
55.2
2026.05
54.7
2026.05
54
2026.05
53
2026.05
52.8
2026.05
52.6
2026.05
52.5
2026.05
52.4
2026.05
52.2
2026.05
51.9
2026.05
51.9
2026.05
51.9
2026.05
49
2026.05
48.2
2026.05
42
2026.05
41.1
2026.05
38.8
2026.05
38.5
2026.05
38.3
2026.05
36.8
2026.05
36.4
2026.05
36.2
2026.05
36.2
2026.05
36.1
2026.05
34.9
2026.05
33.7
2026.05
33.7
2026.05
33.7
2026.05
33.7
2026.05
33.3
2026.05
33.2
2026.05
33.1
2026.05
32.8
2026.05
32.8
2026.05
32.8
2026.05
32.8
2026.05
32.7
2026.05
32.7
2026.05
32.7
2026.05
32.7
2026.05
32.6
2026.05
31.7