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

Question Answering on ARC-E

95.23Accuracy

Direct Fine-tuning

65.69473.36281.0388.698May 17, 2023Oct 31, 2023Apr 16, 2024Oct 1, 2024Mar 17, 2025Sep 1, 2025Feb 16, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2026.02
95.23---
2026.02
95.23---
2026.02
95.12---
2026.02
95.12---
2026.02
95.03---
2026.02
95.01---
2026.02
94.92---
2023.05
89.7---
2026.02
89.26--2.62
2024.04
89---
2026.02
88.5--1.86
2024.04
88.1---
2023.05
88---
2026.02
87.95--1.31
2024.04
87.7---
2026.02
87.06--2.62
2026.02
86.89--2.45
2026.02
86.85--2.41
2026.02
86.74---
2026.02
86.64---
2024.04
86.5---
2023.05
85.6---
2023.05
85---
2023.11
84.7---
2026.02
84.44---
2025.12
84.34---
2025.12
84.13---
2025.12
84.09---
2024.04
83.7---
2025.12
83.54---
2024.04
83.5---
2025.12
83.29---
2024.04
83.2---
2024.04
83.1---
2025.12
82.99---
2025.12
82.95---
2026.01
82.53---
2025.12
82.32---
2025.12
81.81---
2023.11
81.2---
2023.11
80.2---
80.2---
2023.11
79.9---
2023.11
79.4---
2024.05
79.1---
2025.03
78.9-76.9-
2025.03
78.5-76.7-
2024.04
77.7---
2025.09
77.7---
2024.04
77.5---
2024.05
77.5---
2023.11
77.3---
2024.04
77---
2023.11
76.6---
2024.04
76.5---
2024.04
76.3---
2025.03
75.3-72.8-
2023.11
75.2---
2023.07
75.1---
2025.03
75-72.9-
2024.05
74.9---
2023.07
74.9---
2025.03
74.7-73.6-
2023.07
74.6---
2023.07
74.4---
2025.03
74.4-71.3-
2024.05
74.2---
2024.04
73.8---
2023.11
73.6---
2025.03
73.5-71.6-
2023.11
72.8---
2026.02
72.7---
2026.01
72.05---
2024.04
71.9---
2023.11
71.6---
2024.05
71.6---
2024.04
71.5---
71.4---
2024.05
71.1---
2025.02
71---
2025.03
69.8-65.2-
2025.02
69.7---
2025.03
69.6-65.2-
2025.02
69.36---
2025.02
69.14---
2023.11
68.8---
2024.05
68.8---
2025.02
68.6---
2025.02
68.54---
2025.02
68.3---
2024.05
68.2---
2026.01
68.18---
2025.02
68.06---
2025.02
67.47---
2025.02
67.46---
2025.09
67.4---
2025.03
67-62.8-
2025.02
66.96---
2024.05
66.92---
2025.02
66.83---
Showing 100 of 262 rows