DocParsingBench - Text: leaderboard
Systems turn 1,400 pages of real business documents (finance, legal, research, manufacturing, education; Chinese and English) into Markdown; the README does not state how many pages each system was scored on. This board is the text part: half one minus normalized edit distance on text lines, half CDM on inline formulas, after Hungarian matching of segments.
Metric: Text score: 0.5 (1 - NED) + 0.5 inline formula CDM (0-1). Source: github.com. Saturation forecast: Rough model projection: around 2026. 17 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | OXR-1.0 | 0.906 | |
| 2 | Jina-OCR-v1 | 0.8905 | |
| 3 | PaddleOCR-VL-1.6 | 0.8886 | |
| 4 | FireRed-OCR | 0.8802 | |
| 5 | Dots.mocr | 0.8673 | |
| 6 | Infinity-Parser2-Pro | 0.8643 | |
| 7 | TeleOCR | 0.8642 | |
| 8 | Chandra-OCR-2 | 0.8624 | |
| 9 | MinerU2.5-Pro | 0.8622 | |
| 10 | OvisOCR2 | 0.8576 | |
| 11 | Qianfan-OCR | 0.853 | |
| 12 | ABot-OCR | 0.8498 | |
| 13 | GLM-OCR | 0.8372 | |
| 14 | Youtu-Parsing | 0.8134 | |
| 15 | HunyuanOCR 1.5 | 0.7873 |
Interactive version: theaggregate.ai/benchmark?slug=docparsingbench-text · How It Works · Data refreshed daily, snapshot 2026-11-16.