ShredBench - 16 Fragments: leaderboard

Document restoration on ShredBench (2026): news text in two languages, source code and tables are rendered, shredded into 16 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 16 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

#ModelScoreOverall rank
1Gemini 3 Pro0.41#146
2Gemini 3 Flash0.44#180
3Qwen-VL-Plus0.65#5893
4Qwen-VL-Flash0.65
5GLM-4.6V0.71#721
6InternVL3.5-38B0.76#1026
7ShredBench Mistral3-Reas-14B (checkpoint unspecified)0.77
8InternVL3.5-8B0.78#1618
9InternVL3.5-14B0.78#1519
10ShredBench Mistral3-Reas-8B (checkpoint unspecified)0.79
11GPT-5.10.82#248
12GPT-5 Mini0.84#373
13DeepSeek-OCR0.87
14HunyuanOCR0.89

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=shredbench-16-fragments · How It Works · Data refreshed daily, snapshot 2026-11-22.