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

Natural Language Inference on RTE

90Accuracy

LAT

71.07275.98680.985.814Mar 21, 2022Nov 13, 2022Jul 8, 2023Mar 1, 2024Oct 24, 2024Jun 18, 2025Feb 10, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2023.10
90
2023.08
89.8
88.6
2024.05
87
2024.05
86.64
2022.03
86.3
2024.05
86.28
2024.05
86.28
2024.05
86.28
2024.05
85.56
2024.05
85.56
2024.05
85.5
2024.05
85.2
2023.08
85.2
2024.05
85.19
2024.05
84.84
2022.03
84.8
2024.05
84.48
84.48
2024.05
84.12
2024.05
83.75
2024.05
83.75
2024.05
83.6
2024.05
83.6
2024.05
83.3
2024.05
82.7
2024.05
82.31
2025.07
82.31
2025.07
82.31
2022.12
82.17
2022.12
82.1
2023.10
82
2025.07
81.95
2023.05
81.9
2023.11
81.8
2024.05
81.8
2024.05
81.5
2024.05
81.4
2024.05
81.23
2024.05
81.2
2024.05
81.2
2024.05
81.2
2024.05
81.1
2024.05
81.1
2022.12
80.9
2022.12
80.9
2025.07
80.87
2023.02
80.83
2024.05
80.2
2023.11
80.1
2022.12
79.9
2022.12
79.8
2025.07
79.78
2023.05
79.3
2023.11
79.3
2022.03
79.1
2023.05
78.7
2023.05
78.7
2023.11
78.7
2023.11
78.7
2025.07
78.34
2022.12
78.3
2024.05
78.23
2024.05
78
2025.07
77.98
2025.07
77.62
2024.05
76.5
2024.05
76.1
2024.05
75.8
2025.07
75.45
2022.12
75.4
2024.05
75.31
2024.05
75
2024.05
74.8
2024.05
74.8
2025.07
74.73
2025.07
74.73
2025.07
74.73
2024.05
74.7
2025.07
74.37
2025.07
74.37
2024.05
74.1
2024.05
74.1
2024.05
74
2022.12
73.3
2026.02
73.29
2022.11
73.16
2025.05
72.9
2022.11
72.8
2024.05
72.8
2026.02
72.56
2026.02
72.56
2024.05
72.4
2022.12
72.4
2024.05
71.99
2025.07
71.84
2025.07
71.84
2025.07
71.84
2025.07
71.84
2023.04
71.8
Showing 100 of 367 rows