Dr. DocBench: leaderboard
Document parsing and recognition are fundamental capabilities for vision-language models (VLMs) and document processing systems. However, existing Optical Character Recognition (OCR) and document parsing benchmarks are increasingly limited in coverage and difficulty: many focus on common document genres or uniformly sampled pages where modern parsers already perform strongly, while offering limite
Metric: Overall (self-reported). Source: benchmarklist.com. Saturation forecast: Around August 2027. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 61.94 | #31 |
| 2 | Kimi K2.5 | 60.38 | #144 |
| 3 | Claude Opus 4.6 | 60.19 | #63 |
| 4 | Gemini 3.1 Pro (Preview) | 60.13 | #58 |
| 5 | Qwen 3.5 Flash | 57.51 | #232 |
| 6 | Qwen 3.5 Plus | 57.32 | #125 |
| 7 | Qwen 3.5 122B A10B | 56.32 | #173 |
| 8 | GPT-4o | 49.73 | #343 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=dr-docbench · How It Works · Data refreshed daily, snapshot 2026-10-20.