DailyReport (Deep Research Agents) - Factuality: leaderboard
DailyReport (2026) tests search agents on open-ended daily information-seeking tasks about trending topics; each task is split into subtasks with cascade rubrics for instruction following, factuality and rationality, judged by Gemini 3 Flash. This board is the percent of extracted factual claims verified correct by web search, counted where the instruction-following rubric holds, for native deep research agents; higher is better.
Metric: Factuality (0-1 scaled to %), the share of extracted objective claims verified correct by web search, counted only where the instruction-following rubric holds; open-ended daily search tasks on trending topics decomposed into subtasks with cascade rubrics, judged by Gemini 3 Flash; native deep research agents with built-in search, 1,800-second timeout; higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Grok 3 Deep Research | 73.1 | |
| 2 | OpenAI o4-mini Deep Research | 66.3 | |
| 3 | Gemini Deep Research | 63.5 | |
| 4 | OpenAI o3 Deep Research | 61.6 | |
| 5 | Qwen Deep Research | 61.2 |
Interactive version: theaggregate.ai/benchmark?slug=dailyreport-deep-research-agents-factuality · How It Works · Data refreshed daily, snapshot 2026-11-13.