List your company

Language Reasoning on Language Reasoning Average

73.25AccuracyFP16
59.376462.978266.5870.1818Mar 18, 2026

Evaluation results

MethodLinks
FP16Backbone=Qwen2.5-14B2026.0373.25
FP16Backbone=Llama-2-13B2026.0367.23
NSDSBackbone=Qwen2.5-14B2026.0366.15
ZDBackbone=Qwen2.5-14B2026.0365.42
KurtBoostBackbone=Qwen2.5-14B2026.0365.13
MSEBackbone=Qwen2.5-14B2026.0364.29
EWQBackbone=Qwen2.5-14B2026.0363.36
NSDSBackbone=Llama-2-13B2026.0363.01
KurtBoostBackbone=Llama-2-13B2026.0362.08
EWQBackbone=Llama-2-13B2026.0361.68
ZDBackbone=Llama-2-13B2026.0360.99
MSEBackbone=Llama-2-13B2026.0359.91