ShredBench - 8 Fragments: leaderboard
Document restoration on ShredBench (2026): news text in two languages, source code and tables are rendered, shredded into 8 irregular, physically deformed fragments and scattered, and the model restores the content from the fragment images. Normalized edit distance to the original from 0 to 1; lower is better.
Metric: Normalized edit distance (0-1) between the restored and the original document content, aggregated over all ShredBench categories (English and Chinese news, C++, Java and Python code, tables; 756 documents) when each page is shredded into 8 irregular Voronoi fragments rendered with 3D paper deformation and scattered; the model restores the content from the fragment images; temperature 0; lower is better. Source: arxiv.org. Saturation forecast: Around February 2027. 14 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro | 0.33 | #145 |
| 2 | Gemini 3 Flash | 0.34 | #175 |
| 3 | Qwen-VL-Plus | 0.59 | #5818 |
| 4 | Qwen-VL-Flash | 0.59 | |
| 5 | GLM-4.6V | 0.67 | #710 |
| 6 | InternVL3.5-38B | 0.74 | #1021 |
| 7 | InternVL3.5-14B | 0.76 | #1504 |
| 8 | ShredBench Mistral3-Reas-14B (checkpoint unspecified) | 0.76 | |
| 9 | GPT-5.1 | 0.77 | #240 |
| 10 | ShredBench Mistral3-Reas-8B (checkpoint unspecified) | 0.77 | |
| 11 | InternVL3.5-8B | 0.78 | #1604 |
| 12 | GPT-5 Mini | 0.86 | #364 |
| 13 | DeepSeek-OCR | 0.86 | |
| 14 | HunyuanOCR | 0.88 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=shredbench-8-fragments · How It Works · Data refreshed daily, snapshot 2026-11-21.