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

Question Answering on WebQuestions (WebQs)

63.5Accuracy

Gemini2.5-Pro

-2.5414.60531.7548.895May 28, 2020May 10, 2021Apr 23, 2022Apr 6, 2023Mar 19, 2024Mar 2, 2025Feb 13, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
63.5
2026.01
63
2026.01
61.5
2026.01
61.5
2026.01
53.6
2026.02
52.51
2026.01
52.2
2026.01
51.4
2026.01
51.4
2026.02
51.23
2026.01
50.8
2026.01
50.4
2025.07
48.1
2026.01
47.6
2020.05
45.5
2020.05
44.7
2026.01
43.7
2026.02
43.26
2026.02
42.96
2026.02
41.93
2020.05
41.5
2026.01
40.4
2026.01
39.2
2026.02
38.83
2025.07
37.9
2020.05
37.4
2026.02
35.97
2026.01
35.8
2025.07
35.4
2026.02
34.79
2026.02
34.35
2026.02
33.46
2026.01
32.1
2025.07
31.2
2026.02
31.2
2026.02
30.51
2025.07
29.2
2023.02
29
2026.02
28.74
2025.07
28.4
2025.07
28.2
2026.02
26.38
2023.02
26.3
2025.07
26.2
2025.07
25.3
2020.05
25.3
2025.07
24.3
2025.07
23.7
2025.07
21.8
2025.07
21.8
2025.07
21.4
2021.08
19.6
2021.08
19.4
2023.02
18.9
2023.02
18.6
2023.02
18.5
2021.08
18.4
2023.02
18.4
2020.05
14.4
2025.07
4.7
2025.07
4.6
2025.07
1.3
2025.07
0.1
2025.07
0
2025.07
0
2025.07
0
2025.07
0