Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Natural Language Inference on MultiNLI (test) (Matched & Mismatched)

88.05Average Worst-Group Accuracy

Naive + P

63.547669.908876.2782.6312Oct 4, 2024
Updated 3d ago

Evaluation Results

MethodLinks
2024.10
88.05------0.38
2024.10
87.99------0.2
2024.10
87.97------0.3
2024.10
87.86------0.62
2024.10
87.81------0.56
2024.10
87.78------0.31
2024.10
87.75------0.24
2024.10
87.74------0.5
2024.10
87.73------0.3
2024.10
87.7------0.43
2024.10
87.69------0.51
2024.10
87.68------0.12
2024.10
87.57------0.34
2024.10
87.56------0.77
2024.10
87.56------0.46
2024.10
87.56------0.27
2024.10
87.55------0.41
2024.10
87.54------0.34
2024.10
87.54------0.42
2024.10
87.5------0.57
2024.10
87.5------0.55
2024.10
87.45------0.58
2024.10
87.43------1.05
2024.10
87.43------0.48
2024.10
87.37------0.35
2024.10
87.35------0.27
2024.10
87.35------0.19
2024.10
87.32------0.76
2024.10
87.31------0.53
2024.10
87.3------0.78
2024.10
87.29------0.95
2024.10
87.23------0.42
2024.10
87.23------0.49
2024.10
87.22------0.55
2024.10
87.16------0.55
2024.10
87.15------0.82
2024.10
87.14------0.37
2024.10
87.1------0.48
2024.10
87.1------0.14
2024.10
87.04------0.55
2024.10
87.02------0.27
2024.10
86.99------0.26
2024.10
86.89------0.3
2024.10
86.82------0.54
2024.10
86.76------0.54
2024.10
86.75------0.47
2024.10
86.62------0.65
2024.10
86.55------0.3
2024.10
86.53------0.29
2024.10
86.51------0.27
2024.10
86.51------0.58
2024.10
86.47------0.49
2024.10
86.44------0.81
2024.10
86.39------0.76
2024.10
86.23------0.65
2024.10
86.11------0.29
2024.10
86.04------0.93
2024.10
86.02------0.33
2024.10
86.01------0.4
2024.10
85.9------0.43
2024.10
85.84------1.12
2024.10
85.84------0.84
2024.10
85.45------1.1
2024.10
85.41------1.38
2024.10
85.3------1.58
2024.10
85.2------0.24
2024.10
85.1------1.13
2024.10
84.74------0.37
2024.10
84.58------0.37
2024.10
84.38------0.32
2024.10
84.3------0.33
2024.10
84.15------0.3
2024.10
84.13------0.45
2024.10
84.05------0.39
2024.10
83.92------0.25
2024.10
82.41------0.81
2024.10
81.71------0.58
2024.10
81.56------0.75
2024.10
76.54------0.42
2024.10
76.4------0.65
2024.10
64.49------0.9
2018.04
-78.877.8-----
2018.04
-86.785.9-----
2018.04
-79.378.7-----
2019.07
-74.673.6-----
2019.07
-73.273.6-----
2019.07
-78.877.8-----
2019.07
-78.777.9-----
2019.07
-78.978.2-----
2019.07
-8078.7-----
2019.07
-80.279-----
2019.07
-80.379.4-----
2021.02
---83.7----
2021.02
---83.57----
2021.02
---74.8----
2021.02
---75.06----
2021.02
---75.4----
2021.02
---75.5----
2021.02
---76.28----
2023.05
---81.476.6---
Showing 100 of 139 rows