DRFlow (Basic Agent): leaderboard
Metric: Step F1 (%) on the 50-task original split of DRFlow (enterprise deep-research tasks in five domains: predict a personalized workflow of action steps from scattered heterogeneous sources): the task-wise harmonic mean of step recall and precision against the reference workflow (steps matched by an LLM judge), averaged over tasks; a minimal agent without a planning stage that ingests all documents and predicts the workflow directly; higher is better. Source: arxiv.org. Saturation forecast: Around 2031. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.5 | 13.54 |
| 2 | GPT-5.2 | 12.16 |
| 3 | DeepSeek V3.2 | 8.61 |
| 4 | Gemini 3.1 Pro (Preview) | 5.05 |
Interactive version: theaggregate.ai/benchmark?slug=drflow-basic-agent · How It Works · Data refreshed daily, snapshot 2026-09-29.