List your company

Multi-hop Question Answering on MuSiQue (F1, Token Usage, Compression)

68.98F1 ScoreOrgAgent
9.221624.735840.2555.7642Apr 1, 2026

Evaluation results

MethodLinks
OrgAgentBackbone=GPT-5mini, Organization=Hierarchical (AUTO)2026.0468.9811,40837.1159.94
OrgAgentBackbone=GPT-OSS-120B, Organization=Hierarchical (AUTO)2026.0457.5812,04618.9752.22
GPT-5miniOrganization=Baseline2026.0451.282,778——
GPT-5miniOrganization=Flat2026.0450.3128,479——
GPT-OSS-120BOrganization=Flat2026.0448.425,209——
GPT-OSS-120BOrganization=Baseline2026.0437.982,687——
OrgAgentBackbone=LLaMA-3.1-8B, Organization=Hierarchical (AUTO)2026.0432.5912,322123.9976.04
LLaMA-3.1-8BOrganization=Flat2026.0414.5551,425——
LLaMA-3.1-8BOrganization=Baseline2026.0411.522,370——