List your company

Multi-hop Question Answering on 2WikiMultihopQA 6 (test)

68p-hatSPECHOP
12.8827.1941.555.81May 21, 2026

Evaluation results

MethodLinks
SPECHOPTarget Tool (T)=Web Search, Speculator (S)=GPT-4o2026.056819105060
SPECHOPTarget Tool (T)=Web Search, Speculator (S)=GPT-4o mini2026.054116106876
SPECHOPTarget Tool (T)=Web Search, Speculator (S)=Llama 3.1 8B2026.05283107578
SPECHOPTarget Tool (T)=E5 Retrieval, Speculator (S)=Llama 3.1 8B2026.052730748991
SPECHOPTarget Tool (T)=Web Search, Speculator (S)=Qwen 3 8B2026.05185108588
SPECHOPTarget Tool (T)=E5 Retrieval, Speculator (S)=Qwen 3 8B2026.051535749595