# Long PDF Understanding on PaperPDF Chinese 1.0

Source: [Long PDF Understanding on PaperPDF Chinese 1.0](<https://www.sota2.com/research/sota/long-pdf-understanding-on-paperpdf-chinese-1-0>)

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

Data updated: 2026-04-28T09:47:57.187Z

Evaluation of model performance on understanding long documents within the PaperPDF Chinese 1.0 dataset, measured using metrics such as ANLS, F1, Rouge, and GPT-Acc.

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 | Long PDF Understanding |
| Dataset (including any stated split) | PaperPDF Chinese 1.0 |
| Metric | ANLS |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| 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/long-pdf-understanding-on-paperpdf-chinese-1-0.md?metric=ANLS>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/long-pdf-understanding-on-paperpdf-chinese-1-0.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [ROUGE](<https://www.sota2.com/research/sota/long-pdf-understanding-on-paperpdf-chinese-1-0.md?metric=ROUGE>): Higher is better; unit: PERCENT.

- [GPT Accuracy](<https://www.sota2.com/research/sota/long-pdf-understanding-on-paperpdf-chinese-1-0.md?metric=GPT%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | ANLS | Result date | Report paper |
| --- | --- | --- | --- |
| PDF-WuKong | 40.9 | Not recorded | 68fa76ad1e209131cea6e62a |
| InternVL2 | 28.5 | Not recorded | 68fa76ad1e209131cea6e62a |
| InternVL2+BGE-M3\* | 28.4 | Not recorded | 68fa76ad1e209131cea6e62a |
| InternVL2+BGE-M3 | 24.6 | Not recorded | 68fa76ad1e209131cea6e62a |
| InternVL2 | 24.4 | Not recorded | 68fa76ad1e209131cea6e62a |
| Qwen2.5-VL | 23.5 | Not recorded | 68fa76ad1e209131cea6e62a |
| IXC2-VL+BGE-M3 | 23.3 | Not recorded | 68fa76ad1e209131cea6e62a |
| IXC2-VL | 22.5 | Not recorded | 68fa76ad1e209131cea6e62a |
| IXC2-VL | 21.1 | Not recorded | 68fa76ad1e209131cea6e62a |
| MiniCPM-V 2.6 + VisRAG\*(3p) | 20.8 | Not recorded | 68fa76ad1e209131cea6e62a |
| MiniCPM-V 2.6 + VisRAG\*(2p) | 20.5 | Not recorded | 68fa76ad1e209131cea6e62a |
| InternVL2 | 20.3 | Not recorded | 68fa76ad1e209131cea6e62a |
| IXC2-VL | 15.9 | Not recorded | 68fa76ad1e209131cea6e62a |

### PDF-WuKong

ANLS: 40.9. Result ID: 69f0823a47f34ce924d6e1ce.

[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","Token":"2107","Solution Category":"Parsed Interleaved Text and Images"}. This record does not assert independent reproduction.

### InternVL2

ANLS: 28.5. Result ID: 69f0823a47f34ce924d6e1cd.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa73081e209131cea59f8b.md>)

[Implementation](<https://github.com/OpenGVLab/InternVL>)

Recorded evaluation configuration: {"#Param":"8B","Token":"6220","Solution Category":"Parsed Interleaved Text and Images"}. This record does not assert independent reproduction.

### InternVL2+BGE-M3\*

ANLS: 28.4. Result ID: 69f0823a47f34ce924d6e1c6.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa73081e209131cea59f8b.md>)

[Implementation](<https://github.com/OpenGVLab/InternVL>)

Recorded evaluation configuration: {"#Param":"8.5B","Token":"849","Solution Category":"Plain Text Solution"}. This record does not assert independent reproduction.

### InternVL2+BGE-M3

ANLS: 24.6. Result ID: 69f0823a47f34ce924d6e1c5.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa73081e209131cea59f8b.md>)

[Implementation](<https://github.com/OpenGVLab/InternVL>)

Recorded evaluation configuration: {"#Param":"8.5B","Token":"583","Solution Category":"Plain Text Solution"}. This record does not assert independent reproduction.

### InternVL2

ANLS: 24.4. Result ID: 69f0823a47f34ce924d6e1c4.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa73081e209131cea59f8b.md>)

[Implementation](<https://github.com/OpenGVLab/InternVL>)

Recorded evaluation configuration: {"#Param":"8B","Token":"4051","Solution Category":"Plain Text Solution"}. This record does not assert independent reproduction.

### Qwen2.5-VL

ANLS: 23.5. Result ID: 69f0823a47f34ce924d6e1c9.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"#Param":"7B","Token":"5878","Solution Category":"Pure Vision Solution"}. This record does not assert independent reproduction.

### IXC2-VL+BGE-M3

ANLS: 23.3. Result ID: 69f0823a47f34ce924d6e1c3.

[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":"8.5B","Token":"623","Solution Category":"Plain Text Solution"}. This record does not assert independent reproduction.

### IXC2-VL

ANLS: 22.5. Result ID: 69f0823a47f34ce924d6e1cc.

[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","Token":"6217","Solution Category":"Parsed Interleaved Text and Images"}. This record does not assert independent reproduction.

### IXC2-VL

ANLS: 21.1. Result ID: 69f0823a47f34ce924d6e1c2.

[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","Token":"4644","Solution Category":"Plain Text Solution"}. This record does not assert independent reproduction.

### MiniCPM-V 2.6 + VisRAG\*(3p)

ANLS: 20.8. Result ID: 69f0823a47f34ce924d6e1cb.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa74681e209131cea6183d.md>)

[Implementation](<https://github.com/OpenBMB/MiniCPM-V>)

Recorded evaluation configuration: {"#Param":"10B","Token":"2199","Solution Category":"Pure Vision Solution"}. This record does not assert independent reproduction.

### MiniCPM-V 2.6 + VisRAG\*(2p)

ANLS: 20.5. Result ID: 69f0823a47f34ce924d6e1ca.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa74681e209131cea6183d.md>)

[Implementation](<https://github.com/OpenBMB/MiniCPM-V>)

Recorded evaluation configuration: {"#Param":"10B","Token":"1444","Solution Category":"Pure Vision Solution"}. This record does not assert independent reproduction.

### InternVL2

ANLS: 20.3. Result ID: 69f0823a47f34ce924d6e1c8.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa73081e209131cea59f8b.md>)

[Implementation](<https://github.com/OpenGVLab/InternVL>)

Recorded evaluation configuration: {"#Param":"8B","Token":"5008","Solution Category":"Pure Vision Solution"}. This record does not assert independent reproduction.

### IXC2-VL

ANLS: 15.9. Result ID: 69f0823a47f34ce924d6e1c7.

[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","Token":"4712","Solution Category":"Pure Vision Solution"}. This record does not assert independent reproduction.

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