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

Question Answering on Distractor hard

62.2Accuracy (Distractor hard)

NWCAD

Updated 1mo ago

Evaluation Results

Method	Links
NWCAD 2026.04		62.2
Baseline 2026.04		58.4
With-context 2026.04		57.8
NWCAD 2026.04		55.83
AdaCAD 2026.04		54.8
AdaCAD 2026.04		53.21
With-context 2026.04		52.82
NWCAD 2026.04		52.16
CoCoA 2026.04		52
With-context 2026.04		51.25
AdaCAD 2026.04		48.49
Baseline 2026.04		41.42
CAD 2026.04		41.02
Baseline 2026.04		40.81
CoCoA 2026.04		40.5
CoCoA 2026.04		39.71
CAD 2026.04		32.5
CAD 2026.04		29.8