List your company

Deep Research on DeepResearch Bench

58.03RACE OverallDuMate-DeepResearch
33.257239.688646.1252.5514Feb 14, 2026Mar 4, 2026Mar 23, 2026Apr 10, 2026Apr 29, 2026May 17, 2026Jun 5, 2026

Evaluation results

MethodLinks
DuMate-DeepResearchNote=Average scores across multiple runs2026.0658.0359.4861.4853.8754.34———
ZTE Nebula DeepResearch2026.0657.2758.3759.7654.0654.66———
iFlow-Researcher2026.0657.0858.2459.7453.2455.05———
Zhipu Deep Research2026.0657.0658.1560.1453.4753.88———
Xiaoyi DeepResearch 6.02026.065758.5859.3853.5853.99———
Cellcog-Max2026.0656.6757.460.0153.2553.21———
1688AILab-DeepResearch2026.0656.5357.3259.2753.5153.36———
Octen DeepResearch2026.0656.3156.895953.3953.83———
Grep Deep Research2026.0656.2356.8258.9253.3853.44———
NVIDIA-AIQ2026.0655.9556.958.4952.8953.43———
MS-Agent DeepResearch2026.0655.3156.7656.7953.152.28———
Cellcog2026.0655.3155.4158.2152.553.12———
CMCC-DeepInsight2026.0655.2455.6658.752.5350.94———
TrajectoryKit2026.0654.9254.157.952.9152.72———
Onyx Deep Research2026.0654.5454.6756.4353.0852.02———
Bodhi Deep Research2026.0654.2254.2356.0952.8651.81———
AgentDisCoBackbone=Claude-Opus-4.62026.0554.0253.3856.6553.1151.5393.5689.88—
Deep Dog 12026.0653.5253.1456.151.8351.18———
RecallRadar Intelligence2026.0653.1953.9153.5352.1852.38———
DualGraphBackbone LLM=GPT-5, Knowledge Graph Usage=with KG2026.0253.0853.7854.352.4849.8157.5579.65—
Gemini-2.5-ProAgent Configuration=DR2026.0252.5452.6553.251.8251.8372.1153.38—
LiAuto Mind DeepResearch 1.52026.0652.5451.5455.350.4551.26———
Tavily Research2026.0652.4452.8453.5951.9249.21———
ThinkDepth.ai2026.0652.4352.0253.8852.0450.12———
AgentDisCoBackbone=Gemini-2.5-Pro, Harness=true2026.0552.1151.8953.4351.8750.4589.5569.65—
DualGraphBackbone LLM=GPT-4.1, Knowledge Graph Usage=with KG2026.0251.552.075251.4149.356.2376.33—
AgentDisCoBackbone=Gemini-2.5-Pro2026.0551.4451.2352.4951.5750.3989.0663.94—
DualGraphBackbone LLM=GPT-5, Knowledge Graph Usage=without KG2026.0251.1751.6951.7951.1648.7561.1566.06—
Salesforce AIR2026.0650.655051.0950.7750.32———
LangChain Open Deep ResearchComponents=GPT-5 + Gensee Search2026.0650.650.0650.7651.3149.72———
Gemini-2.5-Pro-Deepresearch2026.0549.7149.5149.4550.125078.3165.34—
Gemini 2.5 Pro DeepResearchReproduced=true2026.0649.7149.5149.4550.1250———
DualGraphBackbone LLM=GPT-4.1, Knowledge Graph Usage=without KG2026.0249.1850.1348.4150.0647.3559.9662.96—
OpenAI-DR2026.0246.6847.2745.554845.9373.1831.7—
Doubao-DR2026.0246.6247.6745.2148.1645.0751.8735.12—
KimiAgent Configuration=Res.2026.0246.547.0645.6747.5345.4720.82.3—
Openai-Deepresearch2026.0546.4546.4643.7349.3947.2275.0139.79—
OpenAI DeepResearchReproduced=true2026.0646.4546.4643.7349.3947.22———
UESTC-MBSE-RAAA2026.0646.1343.7748.3447.2143.78———
DR-Tulu2026.0645.4944.0844.6549.5642.3———
Claude-Research2026.054545.3442.7947.5844.66———
Kimi-Research2026.0544.6444.9641.9747.1445.59———
Doubao-Research2026.0544.3444.8440.5647.9544.6952.8652.62—
Langchain-Open-Deep-Research2026.0543.4442.9739.1748.0945.22———
GPT-4.12026.0243.0842.8541.9644.6243.7785.753.84—
LangChain-DR2026.0242.9241.9544.6343.7543.0859.8361.29—
NVIDIA AIQAgent Configuration=RA2026.0242.4842.0141.8143.843.0146.014.41—
PerplexityAgent Configuration=Res.2026.0242.4442.3640.8544.4143.1176.0321.69—
Claude-3.7Agent Configuration=Search2026.0241.5641.4239.9943.842.0287.3224.51—
GrokAgent Configuration=Deep Search2026.0241.0140.5538.8243.5642.8368.477.28—
Qwen-Agent2026.0240.9539.1943.6542.8841.2752.238.39—
Sonar-Reason-Pro2026.0240.744039.0643.1442.337.316.72—
Tongyi-DR2026.0240.6238.6343.9242.5841.03———
Sonar-Reason2026.0240.5339.7338.8742.7942.2651.1911.6—
Sonar-Pro2026.0240.3139.7638.3542.6842.0276.6413.06—
Sonar2026.0237.2936.2634.5140.4640.6169.598.11—
Claude-3.5Agent Configuration=Search2026.0234.3233.4332.3736.9836.3493.88.96—
GPT-4.1-mini2026.0234.2133.3630.5238.1837.6482.634.08—
ASearcher-Web-7BFamily=Open Search2026.05———————10
Claude-Opus-4.52026.06———————50.6
Claude-Sonnet-4.52026.06———————47.2
DecomposeR-8BFamily=Ours, Training Stage=SFT only2026.05———————36.3
DecomposeR-8BFamily=Ours, Training Stage=SFT + RL2026.05———————41.8
Gemini Deep ResearchFamily=DR agent2026.05———————48.9
Gemini-3-Flash High2026.06———————46.1
Gemini-3-pro High2026.06———————49.6
GPT-5 + SearchFamily=LLM+search2026.05———————50.7
GPT-5-mini High2026.06———————50.7
GPT-5.2 High2026.06———————52.2
OpenAI Deep ResearchFamily=DR agent2026.05———————46.9
Perplexity Deep ResearchFamily=DR agent2026.05———————42.7
Qwen3-8B + SearchFamily=LLM+search2026.05———————34.4
Search-R1-7BFamily=Open search2026.05———————9.7
Seed2.0 Lite2026.06———————54.4
Seed2.0 Pro2026.06———————53.3
Tongyi DeepResearch-30B-A3BFamily=Open DR2026.05———————40.6
WebExplorer-8BFamily=Open search2026.05———————36.7
WebThinker QwQ-32BFamily=Open DR2026.05———————37.9
WebThinker-32B-DPOFamily=Open DR2026.05———————40.6