# olmOCR-Bench (olmOCR)

> An end-to-end document understanding benchmark over long, layout-rich PDFs with tables, equations, headers, footnotes, and multi-column flows.

Canonical page: https://benchlm.ai/benchmarks/olmocr

- Category: [Multimodal & Grounded](/multimodal-grounded)
- Last updated: September 27, 2026

## About olmOCR

- Year: 2025
- Tasks: Layout-rich PDF understanding
- Format: Mean accuracy
- Difficulty: Complex document processing
- Paper: [olmOCR-Bench](https://github.com/allenai/olmocr/tree/main/olmocr/bench)

olmOCR-Bench tests whether a system preserves reading order and document structure, not only character-level OCR. BenchLM tracks Interfaze's reported mean score as a display-only document AI benchmark.

olmOCR is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (1 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Interfaze Beta](/models/interfaze-beta) | Interfaze | 85.7% |

## FAQ

### What does olmOCR measure?

An end-to-end document understanding benchmark over long, layout-rich PDFs with tables, equations, headers, footnotes, and multi-column flows.

### Which model scores highest on olmOCR?

Interfaze Beta by Interfaze currently leads with a score of 85.7% on olmOCR.

### How many models are evaluated on olmOCR?

1 AI models have been evaluated on olmOCR on BenchLM.

### Does olmOCR affect BenchLM's overall score?

Not directly. olmOCR is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.