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

Natural Language Inference on SciTail (test)

96.8Accuracy

ALUM_ROBERTA-LARGE-SMART

-7.61619.49246.673.708Dec 30, 2017Dec 12, 2018Nov 25, 2019Nov 7, 2020Oct 21, 2021Oct 4, 2022Sep 17, 2023
Updated 4d ago

Evaluation Results

MethodLinks
2020.04
96.8-
2020.09
96.8-
2020.09
96.8-
2020.04
96.3-
2020.09
96.3-
2022.06
95.7-
2019.11
95.2-
2019.11
95-
2019.01
95-
2020.04
95-
2019.11
94.7-
2019.11
94.4-
2019.01
94.4-
2020.04
94.4-
2019.11
94.2-
2019.11
94.1-
2019.01
94.1-
2020.09
94.1-
2019.11
94-
2021.06
93.4-
2019.11
93.2-
2022.06
93.1-
2021.06
92.72-
2022.06
92.4-
2021.06
92.34-
2019.11
92-
2019.01
92-
2021.06
91.75-
2021.06
91.44-
2021.06
91.27-
2021.06
91.01-
2022.06
90.8-
2022.03
89.5-
2021.06
88.77-
2021.06
88.52-
2018.04
88.4-
2019.11
88.3-
2018.04
88.3-
2019.01
88.3-
2020.04
88.3-
2022.03
88.3-
2021.06
88.22-
2021.06
88.07-
2022.03
87.4-
2022.06
87.4-
2019.08
86.7-
2022.03
86.6-
2021.06
86.55-
2019.08
86-
2018.08
86-
2021.06
85.85-
2018.08
85.1-
2021.06
85.06-
2021.06
84.04-
2017.12
83.3-
2019.08
83.3-
2018.08
83.3-
2021.06
83.25-
2021.06
82-
2021.06
81.97-
2021.06
80.03-
2019.08
80-
2021.06
79.6-
2021.06
79.54-
2023.09
78.928.3
2017.12
77.3-
2018.04
77.3-
2019.08
77.3-
2018.08
77.3-
2017.12
72.3-
2019.08
72.3-
2018.08
72.3-
2017.12
70.8-
2018.08
70.8-
2017.12
70.6-
2017.12
70.6-
2019.08
70.6-
2018.08
70.6-
2018.08
70.6-
2022.03
70.6-
2017.12
60.3-
2023.09
0-49.2
2023.09
0-50.5
2023.09
-0.1-40.2
2023.09
-0.7-31.8
2023.09
-3.6-5.3