# OmniDocBench v1.6 (OmniDocBench 1.6)

> A document parsing benchmark whose overall score composites edit distance, CDM and TEDS sub-scores across diverse PDF layouts.

Canonical page: https://benchlm.ai/benchmarks/omnidocbench16

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

## About OmniDocBench 1.6

- Year: 2024
- Tasks: Document parsing and extraction
- Format: Composite of edit distance, CDM and TEDS
- Difficulty: Grounded document reasoning
- Paper: [OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations](https://arxiv.org/abs/2412.07626)

BenchLM stores OmniDocBench v1.6 on its own higher-is-better key. The v1.5 lane is kept separate because the releases differ in both annotation set and composite definition, and earlier low-is-better error-style rows are not mixed into either key.

OmniDocBench 1.6 is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (1 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Ternary Bonsai 2 27B](/models/ternary-bonsai-2-27b) | Prism ML | 89.1% |

## FAQ

### What does OmniDocBench 1.6 measure?

A document parsing benchmark whose overall score composites edit distance, CDM and TEDS sub-scores across diverse PDF layouts.

### Which model scores highest on OmniDocBench 1.6?

Ternary Bonsai 2 27B by Prism ML currently leads with a score of 89.1% on OmniDocBench 1.6.

### How many models are evaluated on OmniDocBench 1.6?

1 AI models have been evaluated on OmniDocBench 1.6 on BenchLM.

### Does OmniDocBench 1.6 affect BenchLM's overall score?

Not directly. OmniDocBench 1.6 is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.