List your company

Copy on Copy OOD lengths: 2x, 4x, 8x, 16x, 32x, 64x

100Exact Match AccuracySoftmax
-4235077Jun 19, 2025

Evaluation results

MethodLinks
SoftmaxLayers (L)=2, OOD Sequence Length Scale=2x2025.06100
SSMaxLayers (L)=2, OOD Sequence Length Scale=2x2025.06100
SSMaxLayers (L)=2, OOD Sequence Length Scale=4x2025.06100
ASEntmaxLayers (L)=2, OOD Sequence Length Scale=2x2025.06100
SoftmaxLayers (L)=2, OOD Sequence Length Scale=4x2025.0699.9
SoftmaxLayers (L)=2, OOD Sequence Length Scale=8x2025.0699.9
SSMaxLayers (L)=2, OOD Sequence Length Scale=8x2025.0699.9
ASEntmaxLayers (L)=2, OOD Sequence Length Scale=4x2025.0699.9
Top-K (K=32)Layers (L)=2, OOD Sequence Length Scale=2x2025.0699.7
ASEntmaxLayers (L)=2, OOD Sequence Length Scale=8x2025.0699.7
SSMaxLayers (L)=2, OOD Sequence Length Scale=16x2025.0699.6
SoftmaxLayers (L)=2, OOD Sequence Length Scale=16x2025.0699.4
ASEntmaxLayers (L)=2, OOD Sequence Length Scale=16x2025.0699.4
SSMaxLayers (L)=2, OOD Sequence Length Scale=32x2025.0699.3
EntmaxLayers (L)=2, OOD Sequence Length Scale=2x2025.0699
Top-K (K=32)Layers (L)=2, OOD Sequence Length Scale=4x2025.0696.8
ASEntmaxLayers (L)=2, OOD Sequence Length Scale=32x2025.0696.3
SoftmaxLayers (L)=2, OOD Sequence Length Scale=32x2025.0696.1
SSMaxLayers (L)=2, OOD Sequence Length Scale=64x2025.0695.8
ASEntmaxLayers (L)=2, OOD Sequence Length Scale=64x2025.0686.6
EntmaxLayers (L)=2, OOD Sequence Length Scale=4x2025.0686
SoftmaxLayers (L)=2, OOD Sequence Length Scale=64x2025.0685.5
EntmaxLayers (L)=2, OOD Sequence Length Scale=8x2025.0628.5
Top-K (K=32)Layers (L)=2, OOD Sequence Length Scale=8x2025.0626.7
EntmaxLayers (L)=2, OOD Sequence Length Scale=16x2025.060.2
Top-K (K=32)Layers (L)=2, OOD Sequence Length Scale=16x2025.060
Top-K (K=32)Layers (L)=2, OOD Sequence Length Scale=32x2025.060
Top-K (K=32)Layers (L)=2, OOD Sequence Length Scale=64x2025.060
EntmaxLayers (L)=2, OOD Sequence Length Scale=32x2025.060
EntmaxLayers (L)=2, OOD Sequence Length Scale=64x2025.060