# PDF Multimodal Understanding on PaperPDF Single-Evidence Subset

Source: [PDF Multimodal Understanding on PaperPDF Single-Evidence Subset](<https://www.sota2.com/research/sota/pdf-multimodal-understanding-on-paperpdf-single-evidence-subset>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-28T09:47:57.085Z

Evaluation of PDF Multimodal Understanding performance on the PaperPDF Single-Evidence Subset, reporting ANLS, F1, and ROUGE scores.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | PDF Multimodal Understanding |
| Dataset (including any stated split) | PaperPDF Single-Evidence Subset |
| Metric | ANLS |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [ANLS](<https://www.sota2.com/research/sota/pdf-multimodal-understanding-on-paperpdf-single-evidence-subset.md?metric=ANLS>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/pdf-multimodal-understanding-on-paperpdf-single-evidence-subset.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [ROUGE Score](<https://www.sota2.com/research/sota/pdf-multimodal-understanding-on-paperpdf-single-evidence-subset.md?metric=ROUGE%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | ANLS | Result date | Report paper |
| --- | --- | --- | --- |
| PDF-WuKong | 41.5 | Not recorded | 68fa76ad1e209131cea6e62a |
| PDF-WuKong | 36.6 | Not recorded | 68fa76ad1e209131cea6e62a |
| MiniCPM-2.5 | 31.8 | Not recorded | 68fa76ad1e209131cea6e62a |
| Monkey | 30 | Not recorded | 68fa76ad1e209131cea6e62a |
| Qwen-VL | 26.4 | Not recorded | 68fa76ad1e209131cea6e62a |
| Emu2-Chat | 26 | Not recorded | 68fa76ad1e209131cea6e62a |
| CogVLM2 | 24.8 | Not recorded | 68fa76ad1e209131cea6e62a |
| IXC2-4KHD | 24.5 | Not recorded | 68fa76ad1e209131cea6e62a |
| IXC2-VL | 23.4 | Not recorded | 68fa76ad1e209131cea6e62a |
| mPLUG-Owl2 | 19.5 | Not recorded | 68fa76ad1e209131cea6e62a |

### PDF-WuKong

ANLS: 41.5. Result ID: 69f0823a47f34ce924d6e1ac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e62a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e62a.md>)

Recorded evaluation configuration: {"# param":"8.5B","input format":"parsed content as input"}. This record does not assert independent reproduction.

### PDF-WuKong

ANLS: 36.6. Result ID: 69f0823a47f34ce924d6e1ab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e62a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e62a.md>)

Recorded evaluation configuration: {"# param":"8.5B","input format":"page image input"}. This record does not assert independent reproduction.

### MiniCPM-2.5

ANLS: 31.8. Result ID: 69f0823a47f34ce924d6e1a7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e62a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3ab.md>)

Recorded evaluation configuration: {"# param":"8.5B"}. This record does not assert independent reproduction.

### Monkey

ANLS: 30. Result ID: 69f0823a47f34ce924d6e1a4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e62a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74a51e209131cea62ebc.md>)

[Implementation](<https://github.com/Yuliang-Liu/Monkey>)

Recorded evaluation configuration: {"# param":"9.8B"}. This record does not assert independent reproduction.

### Qwen-VL

ANLS: 26.4. Result ID: 69f0823a47f34ce924d6e1a3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e62a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d41e209131cea4d774.md>)

[Implementation](<https://github.com/QwenLM/Qwen-VL>)

Recorded evaluation configuration: {"# param":"9.6B"}. This record does not assert independent reproduction.

### Emu2-Chat

ANLS: 26. Result ID: 69f0823a47f34ce924d6e1a6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e62a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa732a1e209131cea5add9.md>)

[Implementation](<https://github.com/baaivision/Emu>)

Recorded evaluation configuration: {"# param":"37B"}. This record does not assert independent reproduction.

### CogVLM2

ANLS: 24.8. Result ID: 69f0823a47f34ce924d6e1aa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e62a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74a01e209131cea62b64.md>)

Recorded evaluation configuration: {"# param":"17B"}. This record does not assert independent reproduction.

### IXC2-4KHD

ANLS: 24.5. Result ID: 69f0823a47f34ce924d6e1a9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e62a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d01e209131cea58ace.md>)

[Implementation](<https://github.com/InternLM/InternLM-XComposer>)

Recorded evaluation configuration: {"# param":"8B"}. This record does not assert independent reproduction.

### IXC2-VL

ANLS: 23.4. Result ID: 69f0823a47f34ce924d6e1a8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e62a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72021e209131cea541e3.md>)

[Implementation](<https://github.com/InternLM/InternLM-XComposer>)

Recorded evaluation configuration: {"# param":"8B"}. This record does not assert independent reproduction.

### mPLUG-Owl2

ANLS: 19.5. Result ID: 69f0823a47f34ce924d6e1a5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e62a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74bb1e209131cea635b7.md>)

[Implementation](<https://github.com/X-PLUG/mPLUG-DocOwl/tree/main/DocOwl2>)

Recorded evaluation configuration: {"# param":"8.2B"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.