MiroEval (Text-Only) - Process: leaderboard
Metric: Process quality (0-100): audit of the research trajectory (search breadth, analytical depth, progressive refinement, critical thinking, efficiency) on the 70 text-only deep-research tasks; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Doubao Deep Research | 53.1 | #175 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=miroeval-text-only-process · How It Works · Data refreshed daily, snapshot 2026-10-11.