MindEdit-Bench - Chain-of-Thought: leaderboard
All 1,003 MindEdit-Bench questions answered with a step-by-step chain-of-thought prompt instead of the answer-only prompt. Pooled accuracy (%), mean of three runs, higher is better (MindEdit-Bench, Yu et al., ZODA, Zhejiang University and the University of Tokyo, 2026).
Metric: Pooled Accuracy (%), chain-of-thought prompt. Source: arxiv.org. Saturation forecast: Around August 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 35.8 | #91 |
| 2 | GPT-5.4 | 30.1 | #121 |
| 3 | Seed 2.0 Pro | 27.4 | #209 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=mindedit-bench-chain-of-thought · How It Works · Data refreshed daily, snapshot 2026-11-12.