List your company
ResearchFormerly WizWand

Reasoning on AMC 2023 (accuracy)

90.63Accuracy (AMC 2023)DS-Qwen 14B
13.9333.842553.75573.6675May 8, 2025
Updated 8mo ago

Evaluation results

MethodLinks
DS-Qwen 14BModel Size=14B, 0-shot=true2025.0590.63
CATSModel Size=14B, 0-shot=true2025.0588.75
Layer-wise CapreseModel Size=14B, Sparse Algorithm=CATS, 0-shot=true2025.0588.75
E2E CapreseModel Size=14B, Sparse Algorithm=CATS, 0-shot=true2025.0587.5
Layer-wise CapreseModel Size=14B, Sparse Algorithm=GRIFFIN, 0-shot=true2025.0586.88
E2E CapreseModel Size=14B, Sparse Algorithm=GRIFFIN, 0-shot=true2025.0584.38
GRIFFINModel Size=14B, 0-shot=true2025.0580.63
E2E CapreseModel Size=7B, Sparse Algorithm=CATS, 0-shot=true2025.0578.13
DS-Qwen 7BModel Size=7B, 0-shot=true2025.0575
E2E CapreseModel Size=7B, Sparse Algorithm=GRIFFIN, 0-shot=true2025.0571.88
Layer-wise CapreseModel Size=7B, Sparse Algorithm=CATS, 0-shot=true2025.0570
Layer-wise CapreseModel Size=7B, Sparse Algorithm=GRIFFIN, 0-shot=true2025.0564.38
GRIFFINModel Size=7B, 0-shot=true2025.0562.5
CATSModel Size=7B, 0-shot=true2025.0562.5
DS-Qwen 1.5BModel Size=1.5B, 0-shot=true2025.0560.83
Layer-wise CapreseModel Size=1.5B, Sparse Algorithm=CATS, 0-shot=true2025.0548.13
E2E CapreseModel Size=1.5B, Sparse Algorithm=CATS, 0-shot=true2025.0547.5
CATSModel Size=1.5B, 0-shot=true2025.0537.5
E2E CapreseModel Size=1.5B, Sparse Algorithm=GRIFFIN, 0-shot=true2025.0534.38
Layer-wise CapreseModel Size=1.5B, Sparse Algorithm=GRIFFIN, 0-shot=true2025.0528.13
GRIFFINModel Size=1.5B, 0-shot=true2025.0516.88