List your company

Multi-hop Question Answering on MuSiQue 23 (test)

0.5p-hatSPECHOP
0.32320.36910.4150.4609May 21, 2026

Evaluation results

MethodLinks
SPECHOPTarget Tool (T)=Web Search, Speculator (S)=GPT-4o2026.050.50.190.110.630.69
SPECHOPTarget Tool (T)=Web Search, Speculator (S)=GPT-4o mini2026.050.490.20.110.650.72
SPECHOPTarget Tool (T)=E5 Retrieval, Speculator (S)=Llama 3.1 8B2026.050.420.30.640.820.86
SPECHOPTarget Tool (T)=Web Search, Speculator (S)=Llama 3.1 8B2026.050.410.050.110.650.72
SPECHOPTarget Tool (T)=E5 Retrieval, Speculator (S)=Qwen 3 8B2026.050.340.290.640.850.89
SPECHOPTarget Tool (T)=Web Search, Speculator (S)=Qwen 3 8B2026.050.330.050.110.720.78