BaFCo - Layout Analysis (CoT): leaderboard
Metric: Mean average precision at IoU 0.3 (0-100): class-wise average precision of predicted layout boxes, greedily matched to ground truth at IoU 0.3, averaged over the 26 granular entity classes, x100; 200 Bangladeshi government forms (316 pages) with 16,382 annotated entities; chain-of-thought prompt; reasoning_effort low or high as labelled; schema-invalid outputs excluded. Source: arxiv.org. Saturation forecast: Around 2030. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (High) | 11.34 |
| 2 | GPT-5.2 (Low) | 6.43 |
| 3 | GPT-5.2 (High) | 6.15 |
| 4 | Kimi K2.5 (High) | 4.76 |
| 5 | Claude Opus 4.6 (High) | 0.65 |
| 6 | Claude Opus 4.6 (Low) | 0.37 |
Interactive version: theaggregate.ai/benchmark?slug=bafco-layout-analysis-cot · How It Works · Data refreshed daily, snapshot 2026-09-29.