olmOCR-Bench
Chandra OCR 0.1.0 83.1% tops its leaderboard
Not in model cards OCR systems convert 1,403 PDFs to markdown. 7,010 unit tests check text presence and absence, reading order, tables and math.
On Hugging Face's official benchmark list. Many OCR model cards report it.
- Made by
- Allen Institute for AI
- Released
- February 2025
- Kind
- Documents, charts and text in images
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
9
Entries on its own leaderboard, 0 models we track
Chandra OCR 0.1.0 tops the leaderboard with 83.1%
Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.
- 1 Chandra OCR 0.1.0 83.1%
- 2 Infinity-Parser 7B 82.5%
- 3 olmOCR v0.4.0 82.4%
- 4 PaddleOCR-VL 80%
- 5 Marker 1.10.1 76.1%
- 6 DeepSeek-OCR 75.7%
- 7 MinerU 2.5.4 75.2%
- 8 Mistral OCR API 72%
- 9 Nanonets-OCR2-3B 69.5%
Source: Official olmOCR-Bench leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Chandra OCR 0.1.0 | 83.1% | Official leaderboard | ||
| 2 | Infinity-Parser 7B | 82.5% | Official leaderboard | ||
| 3 | olmOCR v0.4.0 | 82.4% | Official leaderboard | ||
| 4 | PaddleOCR-VL | 80% | Official leaderboard | ||
| 5 | Marker 1.10.1 | 76.1% | Official leaderboard | ||
| 6 | DeepSeek-OCR | 75.7% | Official leaderboard | ||
| 7 | MinerU 2.5.4 | 75.2% | Official leaderboard | ||
| 8 | Mistral OCR API | 72% | Official leaderboard | ||
| 9 | Nanonets-OCR2-3B | 69.5% | Official leaderboard |
No lab model card reports it yet
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.
More in Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. GPT-5.1 85.4%
- MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
- CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
- MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy.
Qwen 3.8 Max 97.7% - MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy. Qwen 3.8 Max 85.9%
- ChartQA In use Models answer human-written and generated questions about chart images that need visual and arithmetic reasoning. Scored by relaxed accuracy with a 5 percent numeric tolerance.
Command A Vision 90.9%