Share your thoughts, 1 month free Claude Pro on usSee more

Deep Research on ResearchQA

79.2Score

OpenAI Deep Research

Updated 16d ago

Evaluation Results

Method	Links
OpenAI Deep Research 2025.11		79.2
GPT-5 + Search 2025.11		78.2
DR Tulu-8B (RL) 2025.11		75.7
Perplexity Deep Research 2025.11		75.3
Ai2 ScholarQA - Claude Sonnet 2025.11		75
Gemini 3 Pro + Search 2025.11		74.3
WebThinker-32B-DPO (report) 2025.11		74.2
WebThinker QwQ-32B (report) 2025.11		72.8
Perplexity-Sonar (High) 2025.11		69.1
Gemini Deep Research 2025.11		68.5
DR Tulu-8B (SFT) 2025.11		68.5
Tongyi DeepResearch-30B-A3B 2025.11		66.7
WebExplorer-8B 2025.11		64.8
Claude-Sonnet Search 2025.11		64.3
GPT-5 + Our Search 2025.11		62.8
QwQ-32B 2025.11		60.9
Qwen3-8B 2025.11		56.1
WebThinker-32B-DPO 2025.11		48.6
Qwen3-8B + Our Search 2025.11		46.3
Search-R1-7B 2025.11		27.9
ASearcher-Web-7B 2025.11		19.4