List your company

Multi-step Reasoning on BrowseComp-Plus OOD

54.6Success Rate (SR)Qwen3-Emb + LRAT
7.17619.48831.844.112Mar 30, 2026

Evaluation results

MethodLinks
Qwen3-Emb + LRATAgent Backbone=GLM-4.7 (358B)2026.0354.677.844.6
E5-Large + LRATAgent Backbone=GLM-4.7 (358B)2026.0350.676.344.8
E5-Large + LRATAgent Backbone=MiniMax-M2.1 (229B)2026.0348.769.728.9
Qwen3-Emb + LRATAgent Backbone=MiniMax-M2.1 (229B)2026.0348.369.228.3
E5-LargeAgent Backbone=MiniMax-M2.1 (229B)2026.0346.464.929.1
E5-LargeAgent Backbone=GLM-4.7 (358B)2026.0346.468.744.6
Qwen3-EmbAgent Backbone=GLM-4.7 (358B)2026.0343.966.645.5
Qwen3-EmbAgent Backbone=MiniMax-M2.1 (229B)2026.0338.257.230.8
E5-Large + LRATAgent Backbone=WebExplore (8B)2026.032956.139.1
Qwen3-Emb + LRATAgent Backbone=WebExplore (8B)2026.0327.255.938.7
E5-LargeAgent Backbone=WebExplore (8B)2026.0325.450.440.1
E5-Large + LRATAgent Backbone=Tongyi-DeepResearch (30B)2026.0323.961.841.4
Qwen3-Emb + LRATAgent Backbone=Tongyi-DeepResearch (30B)2026.0323.760.741
Qwen3-EmbAgent Backbone=WebExplore (8B)2026.032147.740.7
E5-LargeAgent Backbone=Tongyi-DeepResearch (30B)2026.0320.754.842.4
Qwen3-EmbAgent Backbone=Tongyi-DeepResearch (30B)2026.0317.849.242.9
E5-LargeAgent Backbone=AgentCPM-Explore (4B)2026.0315.926.540.7
E5-Large + LRATAgent Backbone=AgentCPM-Explore (4B)2026.0315.932.140.1
Qwen3-Emb + LRATAgent Backbone=AgentCPM-Explore (4B)2026.0315.83240.4
Qwen3-EmbAgent Backbone=AgentCPM-Explore (4B)2026.0313.523.240.7
E5-Large + LRATAgent Backbone=GPT-OSS (120B)2026.0313.15644.6
Qwen3-Emb + LRATAgent Backbone=GPT-OSS (120B)2026.0312.156.445.2
E5-LargeAgent Backbone=GPT-OSS (120B)2026.0310.850.144.8
Qwen3-EmbAgent Backbone=GPT-OSS (120B)2026.03943.745.4