InduOCRBench - Formula: leaderboard

The formula recognition score of InduOCRBench (2026), a document-parsing benchmark of 570 real industrial documents in 11 challenge types: Character Detection Matching between rendered predicted and reference formulas, 0 to 100. Higher is better.

Metric: Formula recognition score (0-100): Character Detection Matching (CDM) between the rendered predicted and reference formulas on 570 industrial documents (3,402 pages) in 11 challenge types (complex background, high pixel count, ultra-long, multi-column, ultra-wide, historical books, handwriting, multi-font, visual style, watermark, cross-page tables) plus normal documents, each OCR method converting pages to structured Markdown (general VLMs with a standardized prompt, pipeline tools at default configuration, closed solutions through their official APIs); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 10 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 2.5 Pro77.2#276
2MinerU2.5-2509-1.2B75.4
3Qwen 3 VL 235B A22B Instruct74.8#532
4PaddleOCR-VL74.6
5HunyuanOCR65.6
6Mineru2-pipeline63.2
7DeepSeek-OCR61.8
8GPT-4o58.1#751
9Doc2X56.3
10PP-StructureV353.7

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=induocrbench-formula · How It Works · Data refreshed daily, snapshot 2026-11-21.