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

Out-of-Domain Generalization on AGIEval Law (test)

43.41Average OOD Accuracy

FFA-LoRA

23.036428.325733.61538.9043Oct 6, 2025
Updated 24d ago

Evaluation Results

MethodLinks
2025.10
43.4146.9239.89
2025.10
42.5945.8239.35
2025.10
42.5845.9339.22
2025.10
42.5648.4436.28
2025.10
41.7248.3735.07
2025.10
41.0248.2533.79
2025.10
40.7248.6232.82
2025.10
40.4947.8133.17
2025.10
27.9528.8127.08
2025.10
26.1725.5426.79
2025.10
26.1224.6327.6
2025.10
26.0824.9227.24
2025.10
25.7624.7726.75
2025.10
24.3622.4726.24
2025.10
24.2521.9426.56
2025.10
23.8221.5826.06