List your company

Reasoning on 15 reasoning benchmarks weighted mean (test)

81.35AccuracyCoT
51.60659.32867.0574.772May 20, 2026

Evaluation results

MethodLinks
CoTModel=Qwen3-4B-T, Routing Strategy=CoT2026.0581.35642.5
EDRM-MLPModel=Qwen3-4B-T, Routing Strategy=EDRM-MLP2026.0581.2424.8
StandardModel=Qwen3-4B-T, Routing Strategy=Standard2026.0580.96518.4
EDRM-Inst-EModel=Qwen3-4B-T, Routing Strategy=Inst-E2026.0580.29401.1
EDRM-Inst-CModel=Qwen3-4B-T, Routing Strategy=Inst-C2026.0579.03467.5
EDRM-Global-EModel=Qwen3-4B-T, Routing Strategy=Global-E2026.0578.23335.1
EDRM-Global-CModel=Qwen3-4B-T, Routing Strategy=Global-C2026.0578.23335.1
EDRM-Inst-EModel=Qwen2.5-7B, Routing Strategy=Inst-E2026.0578.11242.7
EDRM-MLPModel=Qwen2.5-7B, Routing Strategy=EDRM-MLP2026.0577.93240.4
Token-SignModel=Qwen3-4B-T, Routing Strategy=Token-Sign2026.0577.65400.6
EDRM-Inst-CModel=Qwen2.5-7B, Routing Strategy=Inst-C2026.0576.91255.3
EDRM-Global-EModel=Qwen2.5-7B, Routing Strategy=Global-E2026.0574.01191.8
EDRM-Global-CModel=Qwen2.5-7B, Routing Strategy=Global-C2026.0574.01190.6
CoTModel=Qwen2.5-7B, Routing Strategy=CoT2026.0573.38330.3
StandardModel=Qwen2.5-7B, Routing Strategy=Standard2026.0572.89240.6
Token-SignModel=Qwen2.5-7B, Routing Strategy=Token-Sign2026.0572.67247.4
EDRM-MLPModel=Llama3.1-8B, Routing Strategy=EDRM-MLP2026.0572.27149.9
EDRM-Inst-EModel=Llama3.1-8B, Routing Strategy=Inst-E2026.0571.97153.9
EDRM-Inst-CModel=Llama3.1-8B, Routing Strategy=Inst-C2026.0571.01170.16
EDRM-Global-EModel=Llama3.1-8B, Routing Strategy=Global-E2026.0568.48164.4
EDRM-Global-CModel=Llama3.1-8B, Routing Strategy=Global-C2026.0568.46167.4
StandardModel=Llama3.1-8B, Routing Strategy=Standard2026.0568.21127.1
CoTModel=Llama3.1-8B, Routing Strategy=CoT2026.0568.07277.8
EDRM-MLPModel=Llama3.2-3B, Routing Strategy=EDRM-MLP2026.0566.64178.9
Token-SignModel=Llama3.1-8B, Routing Strategy=Token-Sign2026.0565.71170.8
DirectModel=Qwen3-4B-T, Routing Strategy=Direct2026.0565.636.2
EDRM-Inst-EModel=Llama3.2-3B, Routing Strategy=Inst-E2026.0565.24179.4
EDRM-Inst-CModel=Llama3.2-3B, Routing Strategy=Inst-C2026.0564.7186.9
DirectModel=Qwen2.5-7B, Routing Strategy=Direct2026.0564.633.4
EDRM-Global-EModel=Llama3.2-3B, Routing Strategy=Global-E2026.0561.89113.2
EDRM-Global-CModel=Llama3.2-3B, Routing Strategy=Global-C2026.0561.89113.2
CoTModel=Llama3.2-3B, Routing Strategy=CoT2026.0560.84251.7
StandardModel=Llama3.2-3B, Routing Strategy=Standard2026.0559.92194.4
Token-SignModel=Llama3.2-3B, Routing Strategy=Token-Sign2026.0559.63184.9
DirectModel=Llama3.1-8B, Routing Strategy=Direct2026.05595
DirectModel=Llama3.2-3B, Routing Strategy=Direct2026.0552.754.4