List your company
ResearchFormerly WizWand

Multi-hop reasoning on MuSiQue Open Book (test)

75.05Accuracy / F1DeCoRe (static)
36.840446.760256.6866.5998Jun 2, 2026
Updated 5mo ago

Evaluation results

MethodLinks
DeCoRe (static)Model=Llama-3-70B, Chain-of-Thought=With CoT2026.0675.05
DoLaModel=Llama-3-70B, Chain-of-Thought=With CoT2026.0674.64
GreedyModel=Llama-3-70B, Chain-of-Thought=With CoT2026.0674.43
ITIModel=Llama-3-70B, Chain-of-Thought=With CoT2026.0674.27
ADModel=Llama-3-70B, Chain-of-Thought=With CoT2026.0674.27
DCO (Ours)Model=Llama-3-70B, Chain-of-Thought=With CoT2026.0674.27
CADModel=Llama-3-70B, Chain-of-Thought=With CoT2026.0674.02
CADModel=Llama-3-8B, Chain-of-Thought=With CoT2026.0673.02
DeCoRe (static)Model=Llama-3-8B, Chain-of-Thought=With CoT2026.0672.49
CDModel=Llama-3-70B, Chain-of-Thought=With CoT2026.0671.7
DoLaModel=Llama-3-8B, Chain-of-Thought=With CoT2026.0669.92
ADModel=Llama-3-8B, Chain-of-Thought=With CoT2026.0669.92
GreedyModel=Llama-3-8B, Chain-of-Thought=With CoT2026.0669.84
DeCoRe (static)Model=Llama-3-70B, Chain-of-Thought=Without CoT2026.0669.76
DCO (Ours)Model=Llama-3-8B, Chain-of-Thought=With CoT2026.0669.01
DoLaModel=Llama-3-70B, Chain-of-Thought=Without CoT2026.0668.68
CADModel=Llama-3-70B, Chain-of-Thought=Without CoT2026.0668.64
GreedyModel=Llama-3-70B, Chain-of-Thought=Without CoT2026.0668.56
ITIModel=Llama-3-70B, Chain-of-Thought=Without CoT2026.0668.14
ADModel=Llama-3-70B, Chain-of-Thought=Without CoT2026.0668.14
DCO (Ours)Model=Llama-3-70B, Chain-of-Thought=Without CoT2026.0667.89
CDModel=Llama-3-70B, Chain-of-Thought=Without CoT2026.0666.61
DeCoRe (static)Model=Llama-3-8B, Chain-of-Thought=Without CoT2026.0661.23
DoLaModel=Llama-3-8B, Chain-of-Thought=Without CoT2026.0659.08
GreedyModel=Llama-3-8B, Chain-of-Thought=Without CoT2026.0658.83
ADModel=Llama-3-8B, Chain-of-Thought=Without CoT2026.0658.63
DCO (Ours)Model=Llama-3-8B, Chain-of-Thought=Without CoT2026.0658.26
CADModel=Llama-3-8B, Chain-of-Thought=Without CoT2026.0657.88
ITIModel=Llama-3-8B, Chain-of-Thought=Without CoT2026.0645.84
ITIModel=Llama-3-8B, Chain-of-Thought=With CoT2026.0638.31