DailyReport (Deep Research Agents) - Factuality: leaderboard
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: Around December 2026. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O3 Deep Research | 61.6 |
Interactive version: theaggregate.ai/benchmark?slug=dailyreport-deep-research-agents-factuality · How It Works · Data refreshed daily, snapshot 2026-09-29.