Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text Classification on SST-2 (Accuracy, OOD, and Path Sensitivity)
Loading...
57.89
Average Accuracy
Task Objective
53.626
54.733
55.84
56.947
May 8, 2026
Average Accuracy
Unseen Accuracy
OOD Accuracy
Path Sensitivity (Logit)
Path Sensitivity (Hidden)
ECE
Updated 22d ago
Evaluation Results
Method
Method
Links
Average Accuracy
Unseen Accuracy
OOD Accuracy
Path Sensitivity (Logit)
Path Sensitivity (Hidden)
ECE
Task Objective
Objective=task
2026.05
57.89
57.92
52.61
0.0078
0.1158
0.45
Full Field Objective
Objective=full
2026.05
55.72
55.72
55.72
0.0592
0.101
9.92
Reveal-path Objective
Objective=reveal
2026.05
53.79
53.8
54.09
4.3906
0.4716
2.5
Feedback
Search any
task
Search any
task