List your company

Information Retrieval and Deep Research on xbench DeepSearch 2505

83.7ScoreStep-3.5-Flash
65.81270.45675.179.744Jun 8, 2026

Evaluation results

MethodLinks
Step-3.5-FlashSize=196B-A11B, Context management=false2026.0683.7
SearchSwarmSize=30B-A3B, Context management=true2026.0680.8
DeepSeek V3.2Size=671B-A37B, Context management=false2026.0678
LongSeekerSize=30B-A3B, Context management=true2026.0678
GPT-5Size=-, Context management=false2026.0677.8
Tongyi DeepResearchSize=30B-A3B, Context management=false2026.0675
Tongyi DR SwarmSize=30B-A3B, Context management=false2026.0675
MiroThinker-1.5-miniSize=30B-A3B, Context management=true2026.0673.1
GLM-4.7Size=355B-A32B, Context management=false2026.0672
MiniMax-M2Size=230B-A10B, Context management=false2026.0672
Claude-4.5-SonnetSize=-, Context management=false2026.0666.5