Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Question Answering on NQ (test)

58.4EM Accuracy

FiE

8.68821.59434.547.406Dec 13, 2021Aug 21, 2022Apr 30, 2023Jan 7, 2024Sep 15, 2024May 25, 2025Feb 1, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2023.05
58.4---
2023.05
56.4---
2023.05
56.3---
2022.12
55.9---
2023.05
55.9---
2022.12
54.7---
2022.12
54.7---
2023.05
54.7---
2022.12
54.4---
2023.05
54.4---
2022.12
54---
2022.12
53.2---
2023.05
53.2---
2022.12
52.5---
2023.05
52.5---
2023.05
51.8---
2022.12
51.4---
2023.05
51.4---
2025.12
47.6---
2022.12
44.5---
2025.12
43.8---
2025.12
43.7---
2026.02
43.5---
2026.02
42.9---
2022.12
42.4---
2025.12
42.3---
2022.12
40.4---
2026.02
39.3---
2025.06
36.48-49.81-
2025.06
36.09-50.18-
2025.12
36---
2025.06
35.71-47.14-
2025.12
34.9---
2025.12
34.8---
2022.12
33.3---
2025.06
32.96-45.32-
2025.06
32.85-44.54-
2021.12
32.5---
2025.06
31.88-44.1-
2025.12
31.8---
2025.06
30.11-42.52-
2026.02
30.1---
2021.12
29.9---
2025.12
29.7---
2025.12
29.4---
2021.12
28.2---
2025.06
27.59-39.19-
2025.06
26.84-38.3-
2021.12
26.3---
2026.02
25---
2025.12
24.9---
2021.12
24.7---
2026.02
24.2---
2026.02
24.1---
2025.12
23.8---
2026.02
23.3---
2021.12
23---
2025.12
22.6---
2025.12
22.4---
2026.02
22.2---
2025.12
15.1---
2021.12
14.6---
2025.12
13.4---
2026.02
12.6---
2025.12
11.1---
2025.12
10.6---
2025.01
-41.8--
2025.01
-51.5--
2025.01
-22--
2025.01
-36--
2025.01
-43.5--
2025.01
-38.4--
2025.01
-42.4--
2025.01
-45.3--
2025.01
-41.3--
2025.01
-46.7--
2025.01
-42.8--
2025.01
-51.9--
2023.11
-0--
2023.11
-29.09--
2023.11
-29.25--
2023.11
-29.64--
2023.12
-50.1--
2023.12
-48.5--
2023.12
-48.9--
2023.12
-47.6--
2023.12
-50.3--
-45.68--
2025.02
-39.9--
2025.02
-40.47--
2025.02
-40.47--
2025.02
-47.41--
2026.02
-28.2-30.8
2026.02
-37.6-38.7
2026.02
-56.5-62.5
2026.02
-54.2-61.1
2026.02
-62.3-67.5
2026.02
-64.9-68.1
2026.02
-68.7-71.7
2026.02
-62.4-66.7
Showing 100 of 150 rows