Khondo (MonoRand): leaderboard
Khondo (2026) document packet splitting on the MonoRand variant of Bangladeshi government form packets (forms of one domain, pages shuffled within each form block), from page images. Packet score from -0.5 to 1: the mean of a clustering score (V-measure and Rand index) and a page-ordering score (Kendall tau-a); higher is better.
Metric: Packet score (-0.5 to 1; mean of the clustering score, the average of V-measure and Rand index, and the ordering score, mean Kendall tau-a over predicted multi-page documents; forms of one domain, pages shuffled within each form block; 210 test packets of 5 to 20 page images of Bangladeshi government forms (Bangla and English, 14 domains); zero-shot order-aware prompt, all page images in one request, JSON output, temperature 1.0, reasoning disabled, invalid outputs retried up to three times). Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.5 Flash (Minimal) | 0.83 | #101 (Gemini 3.5 Flash) |
| 2 | GPT-5.4 (Non-reasoning) | 0.71 | #123 (GPT-5.4) |
| 3 | Qwen 3.6 Plus (Non-reasoning) | 0.71 | #222 (Qwen 3.6 Plus) |
| 4 | GLM-4.6V (Non-reasoning) | 0.46 | #701 (GLM-4.6V) |
| 5 | Kimi K2.5 (Non-reasoning) | 0.42 | #256 (Kimi K2.5) |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=khondo-monorand · How It Works · Data refreshed daily, snapshot 2026-11-13.