List your company
ResearchFormerly WizWand

Long-form research on DRB

50.7ScoreGPT-5 + Search
6.08417.66729.2540.833Nov 24, 2025Dec 22, 2025Jan 19, 2026Feb 16, 2026Mar 16, 2026Apr 13, 2026May 11, 2026
Updated 5mo ago

Evaluation results

MethodLinks
GPT-5 + SearchCategory=Closed Deep Research2026.0550.7
GPT-5 + SearchModel Category=Closed Deep Research2025.1150.7
GPT-5 + Our SearchModel Category=Closed Deep Research2025.1150.3
Gemini Deep ResearchCategory=Closed Deep Research2026.0548.8
Gemini Deep ResearchModel Category=Closed Deep Research, Evaluation Protocol=original author report2025.1148.8
RubricEM-8B (RL, 1400 steps)Backbone=8B, Training=RL, Steps=14002026.0547.8
OpenAI Deep ResearchCategory=Closed Deep Research2026.0546.9
OpenAI Deep ResearchModel Category=Closed Deep Research, Evaluation Protocol=original author report2025.1146.9
Gemini 3 Pro + SearchModel Category=Closed Deep Research2025.1146.3
DR Tulu-8B (RL)Model Category=Open Deep Research (Ours), Training Strategy=RL2025.1145.4
Gemini 3.1 Pro + SearchCategory=Closed Deep Research2026.0544.4
DR Tulu-8B (RL, 1900 steps)Category=Open Deep Research Models, Backbone=8B, Training=RL, Steps=19002026.0543.4
RubricEM-8B (SFT)Backbone=8B, Training=SFT2026.0543
Perplexity Deep ResearchCategory=Closed Deep Research2026.0542.3
Perplexity Deep ResearchModel Category=Closed Deep Research, Evaluation Protocol=original author report2025.1142.3
Perplexity-Sonar (High)Category=Closed Deep Research2026.0540.7
Perplexity-Sonar (High)Model Category=Closed Deep Research, Evaluation Protocol=original author report2025.1140.7
WebThinker-32B-DPOCategory=Fixed Pipeline Deep Research, Backbone=32B, Alignment=DPO2026.0540.6
Tongyi DeepResearch-30B-A3BCategory=Open Deep Research Models, Backbone=30B-A3B2026.0540.6
Tongyi DeepResearch-30B-A3BModel Category=Open Deep Research Models2025.1140.6
WebThinker-32B-DPO (report)Model Category=Fixed Pipeline Deep Research2025.1140.6
QwQ-32BModel Category=Naive RAG2025.1140.3
DR Tulu-8B (SFT)Category=Open Deep Research Models, Backbone=8B, Training=SFT2026.0539
DR Tulu-8B (SFT)Model Category=Open Deep Research (Ours), Training Strategy=SFT2025.1139
WebThinker QwQ-32BCategory=Fixed Pipeline Deep Research, Backbone=QwQ-32B2026.0537.9
WebThinker QwQ-32B (report)Model Category=Fixed Pipeline Deep Research2025.1137.9
WebExplorer-8BCategory=Open Deep Research Models, Backbone=8B2026.0536.7
WebExplorer-8BModel Category=Open Deep Research Models2025.1136.7
Ai2 ScholarQA – Claude SonnetCategory=Fixed Pipeline Deep Research, Backbone=Claude Sonnet2026.0536.1
Ai2 ScholarQA - Claude SonnetModel Category=Fixed Pipeline Deep Research2025.1136.1
Claude-Sonnet SearchCategory=Closed Deep Research2026.0534.5
Claude-Sonnet SearchModel Category=Closed Deep Research, Evaluation Protocol=original author report2025.1134.5
Qwen3-8BModel Category=Naive RAG2025.1133.3
Qwen3-8B + Our SearchBackbone=Qwen3-8B, Search=Our Search2026.0528.2
WebThinker-32B-DPOModel Category=Open Deep Research Models2025.1123.3
Qwen3-8B + Our SearchModel Category=Open Deep Research (Ours)2025.1118.2
Search-R1-7BCategory=Open Deep Research Models, Backbone=R1-7B2026.059.5
Search-R1-7BModel Category=Open Deep Research Models2025.119.5
ASearcher-Web-7BModel Category=Open Deep Research Models2025.117.8