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

Natural Language Inference on SNLI (dev)

93.6Accuracy

ALUM_ROBERTA-LARGE-SMART

31.40847.55463.779.846Sep 22, 2015Dec 31, 2016Apr 12, 2018Jul 22, 2019Oct 31, 2020Feb 9, 2022May 22, 2023
Updated 3d ago

Evaluation Results

MethodLinks
2020.04
93.6
2020.04
93.1
2021.04
93.1
2019.11
92.6
2019.11
92.2
2019.01
92.2
2019.08
92.2
2019.09
92.2
2019.09
92.2
2020.04
92.2
2019.09
92.1
2019.09
92
2019.11
91.7
2019.11
91.7
2019.11
91.7
2019.01
91.7
2020.04
91.7
2019.01
91.5
2019.11
91.4
2019.11
91.4
2019.08
91.4
2019.09
91.3
2019.09
91.2
2023.05
91.03
2019.11
91
2019.01
91
2019.09
90.8
2019.08
90.1
2017.06
87.2
2015.12
86.9
2015.12
86.6
2015.12
86.2
2015.12
85.4
2017.06
84.88
2017.06
83.78
2015.09
83.7
2015.12
83.7
2015.09
83.6
2017.06
83.39
2015.12
83.3
2015.09
83.2
2015.09
83
2015.09
83
2015.12
83
2019.11
82.6
2019.11
82.21
2015.09
82.1
2015.09
81.9
2019.11
81.53
2019.11
81.37
2019.11
81.25
2019.11
81.2
2021.04
81
2019.11
80.48
2023.05
80.16
2023.05
80.11
2023.05
80.11
2023.05
80.09
2023.05
80
2019.11
79.9
2019.11
78.4
2023.05
77.99
2023.05
77.72
2021.04
77.6
2019.11
77.4
2019.11
77.11
2023.05
76.96
2019.11
75.67
2021.04
52
2021.04
38.4
2021.04
33.8