List your company

Deep Research on ResearchQA

79.2ScoreOpenAI Deep Research
17.00833.15449.365.446Nov 24, 2025Dec 27, 2025Jan 29, 2026Mar 3, 2026Apr 5, 2026May 8, 2026Jun 10, 2026

Evaluation results

MethodLinks
OpenAI Deep ResearchModel Category=Closed Deep Research, Evaluation Protocol=100-sample subset2025.1179.2
OpenAI Deep ResearchCategory=Closed Deep Research2026.0679.2
GPT-5 + SearchModel Category=Closed Deep Research, Evaluation Protocol=100-sample subset2025.1178.2
GPT-5 + SearchCategory=Closed Deep Research2026.0678.2
HOTE-8BCategory=Open Evolving Deep Research2026.0676.9
DR Tulu-8B (RL)Model Category=Open Deep Research (Ours), Training Strategy=RL2025.1175.7
Perplexity Deep ResearchModel Category=Closed Deep Research, Evaluation Protocol=original author report2025.1175.3
GSPOCategory=RL Methods2026.0675.1
Ai2 ScholarQA - Claude SonnetModel Category=Fixed Pipeline Deep Research, Evaluation Protocol=100-sample subset2025.1175
Ai2 ScholarQA-Claude Sonnet (report)Category=Fixed Pipeline Deep Research2026.0675
REINFORCE++Category=RL Methods2026.0674.8
Gemini 3 Pro + SearchModel Category=Closed Deep Research2025.1174.3
Gemini 3 Pro + SearchCategory=Closed Deep Research2026.0674.3
DR Tulu-8B-RLCategory=Open Deep Research2026.0674.3
WebThinker-32B-DPO (report)Model Category=Fixed Pipeline Deep Research2025.1174.2
WebThinker-32B-DPO (report)Category=Fixed Pipeline Deep Research2026.0674.2
SPICE-8BCategory=Evolving Methods2026.0673.9
GRPOCategory=RL Methods2026.0673.5
Dr. Zero-8BCategory=Evolving Methods2026.0673.2
WebThinker QwQ-32B (report)Model Category=Fixed Pipeline Deep Research2025.1172.8
WebThinker QwQ-32B (report)Category=Fixed Pipeline Deep Research2026.0672.8
Perplexity-Sonar (High)Model Category=Closed Deep Research, Evaluation Protocol=original author report2025.1169.1
Gemini Deep ResearchModel Category=Closed Deep Research, Evaluation Protocol=original author report2025.1168.5
DR Tulu-8B (SFT)Model Category=Open Deep Research (Ours), Training Strategy=SFT2025.1168.5
DR Tulu-8B-SFTCategory=Open Deep Research2026.0668.5
Tongyi DeepResearch-30B-A3BModel Category=Open Deep Research Models2025.1166.7
Tongyi DeepResearch-30B-A3BCategory=Open Deep Research Models2026.0666.7
WebExplorer-8BModel Category=Open Deep Research Models2025.1164.8
WebExplorer-8BCategory=Open Deep Research Models2026.0664.8
Claude-Sonnet SearchModel Category=Closed Deep Research, Evaluation Protocol=original author report2025.1164.3
GPT-5 + Our SearchModel Category=Closed Deep Research2025.1162.8
QwQ-32BModel Category=Naive RAG2025.1160.9
Qwen3-8BModel Category=Naive RAG2025.1156.1
Qwen3-235B-A22BCategory=Open Deep Research Models2026.0650.7
WebThinker-32B-DPOModel Category=Open Deep Research Models2025.1148.6
WebThinker-32B-DPOCategory=Open Deep Research Models2026.0648.6
Qwen3-8B + Our SearchModel Category=Open Deep Research (Ours)2025.1146.3
Qwen3-8BCategory=Open Deep Research Models2026.0646.3
Search-R1-7BModel Category=Open Deep Research Models2025.1127.9
Search-R1-7BCategory=Open Deep Research Models2026.0627.9
ASearcher-Web-7BModel Category=Open Deep Research Models2025.1119.4
ASearcher-Web-7BCategory=Open Deep Research Models2026.0619.4