Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Abstention Classification on NaturalQA (test)
Loading...
100
Accuracy (Abs=0)
OTC
58.608
69.354
80.1
90.846
Oct 1, 2025
Accuracy (Abs=0)
Delta Score
Updated 5d ago
Evaluation Results
Method
Method
Links
Accuracy (Abs=0)
Delta Score
OTC
2025.10
100
0
Ternary
2025.10
100
0
MASH w/ OTC
2025.10
99.9
0.1
AFH
mode=Multisample
2025.10
87.9
52.1
MASH w/ EXP
2025.10
85.6
62.7
MASH w/ OTC-ST
2025.10
85.4
66.1
DPO
2025.10
84.5
71.6
AFH
mode=Absolute
2025.10
67.7
48.1
Prompting
shots=5-shot
2025.10
60.2
44.6
Feedback
Search any
task
Search any
task