List your company

Deep-search QA on Xbench-DeepSearch (test)

75Pass@1Tongyi-DR-30B
21.9635.7349.563.27Feb 8, 2026

Evaluation results

MethodLinks
Tongyi-DR-30BBackbone=30B, Type=Open-Source Agentic Foundation Model2026.0275
DeepSeek-V3.1Type=Open-Source Agentic Foundation Model2026.0271
MiroThinker-v1.0-30BBackbone=30B, Type=Open-Source Agentic Foundation Model2026.0270.6
GLM-4.6Type=Open-Source Agentic Foundation Model2026.0270
OpenAI-o3Type=Proprietary Agentic Foundation Model2026.0267
Claude-4.5-SonnetType=Proprietary Agentic Foundation Model2026.0266
QwQ-32B-RFT-Iter2 (SRR-Judge)Backbone=QwQ-32B, Training Strategy=Iterative RFT, Iteration=2, Supervision Type=SRR-Judge2026.0261.3
Kimi-K2-0905Type=Open-Source Agentic Foundation Model2026.0261
QwQ-32B-RFT-Iter1 (SRR-Judge)Backbone=QwQ-32B, Training Strategy=Iterative RFT, Iteration=1, Supervision Type=SRR-Judge2026.0259.7
QwQ-32B-RFT-Iter1 (ORM)Backbone=QwQ-32B, Training Strategy=Iterative RFT, Iteration=1, Supervision Type=Outcome Supervision (ORM)2026.0256.5
DeepSeek-R1 + SRR RefineBackbone=DeepSeek-R1, Refinement Method=SRR Refine2026.0255.3
QwQ-32B-SFT + SRR RefineBackbone=QwQ-32B, Training Strategy=SFT, Refinement Method=SRR Refine2026.0255
DeepSeek-R1Backbone=DeepSeek-R12026.0253.7
WebSailor-32BBackbone=32B, Type=Open-Source Deep Search Solution2026.0253.3
QwQ-32B + SRR RefineBackbone=QwQ-32B, Refinement Method=SRR Refine2026.0253.3
QwQ-32B-SFTBackbone=QwQ-32B, Training Strategy=SFT2026.0252.7
DeepDive-32BBackbone=32B, Type=Open-Source Deep Search Solution2026.0251.8
Grok-DeepResearchType=Proprietary Agentic Foundation Model2026.0250
Doubao-DeepThinkType=Proprietary Agentic Foundation Model2026.0250
QwQ-32BBackbone=QwQ-32B2026.0246
ASearcher-Web-32BBackbone=32B, Type=Open-Source Deep Search Solution2026.0242.1
WebDancer-32BBackbone=32B, Type=Open-Source Deep Search Solution2026.0239
Search-O1-32BBackbone=32B, Type=Open-Source Deep Search Solution2026.0225
WebThinker-32BBackbone=32B, Type=Open-Source Deep Search Solution2026.0224