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

Question Answering on ARC Challenge (test)

64.25Accuracy

FP16

16.25428.714541.17553.6355Apr 24, 2020Apr 12, 2021Mar 31, 2022Mar 19, 2023Mar 6, 2024Feb 22, 2025Feb 11, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2024.03
64.25---
2026.01
60.07---
2026.01
59.22---
2026.01
54.95---
2026.01
54.78---
2024.03
53.33---
2024.05
51.4---
2024.05
51.4---
2026.01
51.11---
2024.05
51---
2020.04
48.545.212.411
2020.04
48.243.813.110.7
2020.04
48.143.412.910.8
2024.03
47.53---
2020.04
47.542.213.910.8
2026.01
46.42---
2026.01
46.33---
2024.05
45---
2026.01
44.03---
2024.03
43.34---
2020.04
43.142.46.69.3
2026.01
42.66---
2024.05
42---
2020.04
39.435.26.69.3
2024.05
39.2---
2026.01
39.08---
2024.05
39---
2026.01
38.99---
2026.01
38.91---
2026.02
38.8---
2024.05
37.2---
2024.05
37---
2024.05
37---
2026.02
36.9---
2026.02
35.6---
2026.01
35.49---
2026.01
33.96---
2023.04
31.8---
2023.04
31.3---
2024.05
30.2---
2023.04
29.5---
2026.02
28.4---
2026.02
28.3---
2024.07
28---
2024.07
27.5---
2024.07
26.6---
2024.07
26.6---
2023.04
26---
2024.07
25.4---
2026.02
24.8---
2026.02
24.63---
2023.04
24.4---
2026.02
24.34---
2026.02
24---
2026.02
23.82---
2024.07
23.5---
2024.07
23---
2024.07
22.4---
2024.07
22.3---
2024.07
22.1---
2023.04
21.3---
2023.04
18.8---
2023.04
18.1---