Mr Dre - Content Feedback Incorporation Rate: leaderboard
Multi-turn report revision by deep research agents on Mr Dre (Chen et al., 2026): after a first report on an expert-written research question from ResearchRubrics, RigorousBench or ResearcherBench, the agent receives simulated user feedback naming checklist content the report missed and revises the report. Incorporation rate in percent is the share of the fed-back criteria fully covered after the revision, judged by GPT-4.1-mini and averaged over the three question sets; higher is better.
Metric: Incorporation rate (%; turn-2 revision after content feedback: share of the fed-back checklist criteria fully covered in the revised report; averaged over ResearchRubrics, RigorousBench and ResearcherBench questions; GPT-4.1-mini judge). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | OpenAI o4-mini Deep Research | 93.6 | |
| 2 | LangChain Open Deep Research (GPT-4.1-mini) | 93 | |
| 3 | Sonar Deep Research | 92.6 | |
| 4 | dr-tulu | 90.3 | |
| 5 | Tongyi-DeepResearch-30B-A3B | 90.2 |
Interactive version: theaggregate.ai/benchmark?slug=mr-dre-content-feedback-incorporation-rate · How It Works · Data refreshed daily, snapshot 2026-11-12.