List your company

Deep Research on GAIA text-only original (test)

74.1Pass@1WebSailor-v2-30B-A3B (RL)
31.35642.45353.5564.647Jan 26, 2026

Evaluation results

MethodLinks
WebSailor-v2-30B-A3B (RL)Backbone Group=Medium Size Deep Research Agents (30B-72B), Training Protocol=RL2026.0174.1
Tongyi-DeepResearchBackbone Group=Medium Size Deep Research Agents (30B-72B)2026.0170.9
OpenAI-o3Backbone Group=Large Size Foundation Models (> 100B)2026.0170.5
Claude-4-SonnetBackbone Group=Large Size Foundation Models (> 100B)2026.0168.3
WebSailor-v2-30B-A3B (SFT)Backbone Group=Medium Size Deep Research Agents (30B-72B), Training Protocol=SFT2026.0166
DeepSeek-V3.2Backbone Group=Large Size Foundation Models (> 100B)2026.0163.5
DeepSeek-V3.1Backbone Group=Large Size Foundation Models (> 100B)2026.0163.1
WebShaper-72BBackbone Group=Medium Size Deep Research Agents (30B-72B)2026.0160
Kimi-K2Backbone Group=Large Size Foundation Models (> 100B)2026.0157.7
MiroThinker-32B-DPO-v0.1Backbone Group=Medium Size Deep Research Agents (30B-72B), Training Protocol=DPO2026.0157.3
WebSailor-72BBackbone Group=Medium Size Deep Research Agents (30B-72B)2026.0155.4
WebSailor-32BBackbone Group=Medium Size Deep Research Agents (30B-72B)2026.0153.2
ASearcher-Web-QwQBackbone Group=Medium Size Deep Research Agents (30B-72B)2026.0152.8
WebShaper-32BBackbone Group=Medium Size Deep Research Agents (30B-72B)2026.0152.4
WebDancer-QwQBackbone Group=Medium Size Deep Research Agents (30B-72B)2026.0151.5
OffSeeker-8B (DPO)Backbone Group=Small Size Deep Research Agents (< 10B), Training Protocol=DPO2026.0151.5
WebExplorer-8B (RL)Backbone Group=Small Size Deep Research Agents (< 10B), Training Protocol=RL2026.0147.6
OffSeeker-8B (SFT)Backbone Group=Small Size Deep Research Agents (< 10B), Training Protocol=SFT2026.0147.6
MiroThinker-8B-DPO-v0.1Backbone Group=Small Size Deep Research Agents (< 10B), Training Protocol=DPO2026.0146.6
WebSailor-7BBackbone Group=Small Size Deep Research Agents (< 10B)2026.0133