List your company

Reverse on Reverse OOD lengths: 1.5x, 2x, 4x, 8x

100Exact Match AccuracyTop-K (K=32)
-4235077Jun 19, 2025

Evaluation results

MethodLinks
Top-K (K=32)Layers (L)=6, OOD Sequence Length Scale=1.5x2025.06100
ASEntmaxLayers (L)=6, OOD Sequence Length Scale=1.5x2025.06100
ASEntmaxLayers (L)=6, OOD Sequence Length Scale=2x2025.0699.8
EntmaxLayers (L)=6, OOD Sequence Length Scale=1.5x2025.0699
Top-K (K=32)Layers (L)=6, OOD Sequence Length Scale=2x2025.0698.7
ASEntmaxLayers (L)=6, OOD Sequence Length Scale=4x2025.0696.4
EntmaxLayers (L)=6, OOD Sequence Length Scale=2x2025.0686
Top-K (K=32)Layers (L)=6, OOD Sequence Length Scale=4x2025.0657
ASEntmaxLayers (L)=6, OOD Sequence Length Scale=8x2025.0656.7
SSMaxLayers (L)=6, OOD Sequence Length Scale=1.5x2025.0654.6
SoftmaxLayers (L)=6, OOD Sequence Length Scale=1.5x2025.0636
EntmaxLayers (L)=6, OOD Sequence Length Scale=4x2025.0628.5
EntmaxLayers (L)=6, OOD Sequence Length Scale=8x2025.060.2
SoftmaxLayers (L)=6, OOD Sequence Length Scale=2x2025.060
SoftmaxLayers (L)=6, OOD Sequence Length Scale=4x2025.060
SoftmaxLayers (L)=6, OOD Sequence Length Scale=8x2025.060
Top-K (K=32)Layers (L)=6, OOD Sequence Length Scale=8x2025.060
SSMaxLayers (L)=6, OOD Sequence Length Scale=2x2025.060
SSMaxLayers (L)=6, OOD Sequence Length Scale=4x2025.060
SSMaxLayers (L)=6, OOD Sequence Length Scale=8x2025.060