List your company

Multi-hop Question Answering on SQuAD

25.8Exact Match (EM)ZipRL-8B
4.58410.09215.621.108May 27, 2026

Evaluation results

MethodLinks
ZipRL-8BMethod Strategy=Specialized Agent, Backbone=Qwen3-8B2026.0525.842.4
ZipRL-7BMethod Strategy=Specialized Agent, Backbone=Qwen2.5-7B2026.0525.643
ZipRL-3BMethod Strategy=Specialized Agent, Backbone=Qwen2.5-3B2026.0525.240.3
ASearcher-14BMethod Strategy=Specialized Agent, Backbone=Qwen2.5-14B2026.0524.441.6
ZipRL-14BMethod Strategy=Specialized Agent, Backbone=Qwen3-14B2026.052442.2
ASearcher-7BMethod Strategy=Specialized Agent, Backbone=Qwen2.5-7B2026.0523.839.5
ZipRL-14BMethod Strategy=Specialized Agent, Backbone=Qwen2.5-14B2026.0523.241
ZipRL-4BMethod Strategy=Specialized Agent, Backbone=Qwen3-4B2026.052339
AgentFold-14BMethod Strategy=Specialized Agent, Backbone=Qwen3-14B2026.0521.836.5
Gemini-3-Pro-ReActMethod Strategy=ReAct, Backbone=Gemini-3-Pro2026.0521.438.2
AgentFold-8BMethod Strategy=Specialized Agent, Backbone=Qwen3-8B2026.0520.834.9
AgentFold-4BMethod Strategy=Specialized Agent, Backbone=Qwen3-4B2026.0519.433.8
NestBrowse-8BMethod Strategy=Specialized Agent, Backbone=Qwen3-8B2026.0519.236.9
LongCat-Flash-ReActMethod Strategy=ReAct, Backbone=LongCat-Flash2026.0518.635.3
Qwen3-235B-ReActMethod Strategy=ReAct, Backbone=Qwen3-235B2026.0517.832.3
WebSailor-32BMethod Strategy=Standard, Backbone=WebSailor-32B2026.0517.437.3
NestBrowse-14BMethod Strategy=Specialized Agent, Backbone=Qwen3-14B2026.0515.230.3
NestBrowse-4BMethod Strategy=Specialized Agent, Backbone=Qwen3-4B2026.0514.628.5
Qwen3-235B-SummaryMethod Strategy=Summary, Backbone=Qwen3-235B2026.051328.1
WebSailor-7BMethod Strategy=Specialized Agent, Backbone=Qwen2.5-7B2026.051326.4
LongCat-Flash-SummaryMethod Strategy=Summary, Backbone=LongCat-Flash2026.0512.829.5
DeepSeek-V3.2-SummaryMethod Strategy=Summary, Backbone=DeepSeek-V3.22026.0512.230.6
Search-R1-14BMethod Strategy=Specialized Agent, Backbone=Qwen2.5-14B2026.0511.420.5
Gemini-3-Pro-SummaryMethod Strategy=Summary, Backbone=Gemini-3-Pro2026.0510.425.5
DeepSeek-V3.2-ReActMethod Strategy=ReAct, Backbone=DeepSeek-V3.22026.0510.222.9
Search-R1-3BMethod Strategy=Specialized Agent, Backbone=Qwen2.5-3B2026.058.817.6
GPT-4o-ReActMethod Strategy=ReAct, Backbone=GPT-4o2026.058.624.5
GPT-4o-SummaryMethod Strategy=Summary, Backbone=GPT-4o2026.055.619.7
WebSailor-3BMethod Strategy=Specialized Agent, Backbone=Qwen2.5-3B2026.055.617.8
Search-R1-7BMethod Strategy=Specialized Agent, Backbone=Qwen2.5-7B2026.055.413.1