Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Natural Language Understanding on GLUE (NLI, MRPC, QNLI, QQP Subset)
Loading...
50.21
NLI Accuracy
Pre-edited
32.8732
37.3741
41.875
46.3759
Jan 16, 2026
NLI Accuracy
MRPC Accuracy
QNLI Accuracy
QQP Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
NLI Accuracy
MRPC Accuracy
QNLI Accuracy
QQP Accuracy
Pre-edited
Backbone=LLaMA2, Numbe...
2026.01
50.21
81.52
49.92
53.35
HORSE
Backbone=LLaMA2, Numbe...
2026.01
50.18
80.31
53.25
54.06
MALMEN
Backbone=LLaMA2, Numbe...
2026.01
47.48
34.66
51.03
27.38
PMET
Backbone=LLaMA2, Numbe...
2026.01
46.13
42.52
49.59
53.47
MEMIT
Backbone=LLaMA2, Numbe...
2026.01
43.12
81.23
49.46
53.83
MEND
Backbone=LLaMA2, Numbe...
2026.01
33.54
0
50.54
0
Feedback
Search any
task
Search any
task