# OCRBench

OCRBench is an AI benchmark; this page records what it measures and traces its data, grader, and scores to primary sources.

Measures OCR in multimodal models across text recognition, scene-text VQA, document VQA, extraction, and handwritten math.

## Details

- Address: Online, Global
- Website: [github.com/Yuliang-Liu/MultimodalOCR/tree/main/OCRBench](<https://github.com/Yuliang-Liu/MultimodalOCR/tree/main/OCRBench>)
- Tags: Helpful, Science
- Category: Multimodal
- Status: Active
- Data licence: MIT
- Data access: open
- Grader: mixed
- Organization: OCRBench authors
- Released: 2023-05
- Paper: [arxiv.org/abs/2305.07895](<https://arxiv.org/abs/2305.07895>)
- Repository: [github.com/Yuliang-Liu/MultimodalOCR](<https://github.com/Yuliang-Liu/MultimodalOCR>)
- Task count: 1,000
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is OCRBench?

OCRBench is at Online, Global.

### How do I contact OCRBench?

To contact OCRBench, visit https://github.com/Yuliang-Liu/MultimodalOCR/tree/main/OCRBench.

## Source

From [Benchmark primary sources](https://aibenchmarkindex.com/about), license CC0-1.0, checked 2026-10-15.

Last updated October 15, 2026.

## Links

- This benchmark on the [web page](<https://aibenchmarkindex.com/global/online/ocrbench>)
- [Multimodal in Online](<https://aibenchmarkindex.com/global/online/category/multimodal.md>)
- [More benchmarks in Online](<https://aibenchmarkindex.com/global/online.md>)

> **Check before you compare.** Benchmark methods and leaderboards change. Follow the cited primary source before using a result in a decision.