# Standardization on Chinese clinical diagnostic reports

Source: [Standardization on Chinese clinical diagnostic reports](<https://www.sota2.com/research/sota/standardization-on-chinese-clinical-diagnostic-reports>)

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

Data updated: 2026-02-26T05:37:13.627Z

Evaluation of text standardization performance on the Chinese clinical diagnostic reports dataset, measured using metrics such as BLEU, METEOR, and ROUGE.

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 | Standardization |
| Dataset (including any stated split) | Chinese clinical diagnostic reports |
| Metric | BLEU-1 |
| 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

- [BLEU-1](<https://www.sota2.com/research/sota/standardization-on-chinese-clinical-diagnostic-reports.md?metric=BLEU-1>): Higher is better; unit: PERCENT.

- [BLEU-4](<https://www.sota2.com/research/sota/standardization-on-chinese-clinical-diagnostic-reports.md?metric=BLEU-4>): Higher is better; unit: PERCENT.

- [METEOR](<https://www.sota2.com/research/sota/standardization-on-chinese-clinical-diagnostic-reports.md?metric=METEOR>): Higher is better; unit: PERCENT.

- [ROUGE-L](<https://www.sota2.com/research/sota/standardization-on-chinese-clinical-diagnostic-reports.md?metric=ROUGE-L>): Higher is better; unit: PERCENT.

## Recorded results

| Method | BLEU-1 | Result date | Report paper |
| --- | --- | --- | --- |
| RetSTA-7B | 93.35 | Not recorded | 68fa77681e209131cea7314b |
| RetSTA-7B-Zero | 91.93 | Not recorded | 68fa77681e209131cea7314b |
| GLM-4-Plus | 83 | Not recorded | 68fa77681e209131cea7314b |
| DeepSeek-V3 | 82.92 | Not recorded | 68fa77681e209131cea7314b |
| Qwen2.5-72B-Instruct | 81.97 | Not recorded | 68fa77681e209131cea7314b |
| Llama-3.1-8B-Chinese-Chat | 79.02 | Not recorded | 68fa77681e209131cea7314b |
| Qwen2.5-7B-Instruct | 76.83 | Not recorded | 68fa77681e209131cea7314b |
| GLM-4-9B | 74.77 | Not recorded | 68fa77681e209131cea7314b |
| Baichuan2-7B-Chat | 73.46 | Not recorded | 68fa77681e209131cea7314b |
| Yi-1.5-9B-Chat | 70.31 | Not recorded | 68fa77681e209131cea7314b |

### RetSTA-7B

BLEU-1: 93.35. Result ID: 699487b03a6c3148491dd1c0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77681e209131cea7314b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77681e209131cea7314b.md>)

[Implementation](<https://github.com/AB-Story/RetSTA-7B>)

Recorded evaluation configuration: {"Model size category":"\<10B"}. This record does not assert independent reproduction.

### RetSTA-7B-Zero

BLEU-1: 91.93. Result ID: 699487b03a6c3148491dd1bf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77681e209131cea7314b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77681e209131cea7314b.md>)

[Implementation](<https://github.com/AB-Story/RetSTA-7B>)

Recorded evaluation configuration: {"Model size category":"\<10B"}. This record does not assert independent reproduction.

### GLM-4-Plus

BLEU-1: 83. Result ID: 699487b03a6c3148491dd1c2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77681e209131cea7314b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74521e209131cea610b6.md>)

Recorded evaluation configuration: {"Model size category":"\>10B"}. This record does not assert independent reproduction.

### DeepSeek-V3

BLEU-1: 82.92. Result ID: 699487b03a6c3148491dd1c3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77681e209131cea7314b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77001e209131cea7066a.md>)

Recorded evaluation configuration: {"Model size category":"\>10B"}. This record does not assert independent reproduction.

### Qwen2.5-72B-Instruct

BLEU-1: 81.97. Result ID: 699487b03a6c3148491dd1c1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77681e209131cea7314b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa767e1e209131cea6d6a7.md>)

Recorded evaluation configuration: {"Model size category":"\>10B"}. This record does not assert independent reproduction.

### Llama-3.1-8B-Chinese-Chat

BLEU-1: 79.02. Result ID: 699487b03a6c3148491dd1bc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77681e209131cea7314b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

Recorded evaluation configuration: {"Model size category":"\<10B"}. This record does not assert independent reproduction.

### Qwen2.5-7B-Instruct

BLEU-1: 76.83. Result ID: 699487b03a6c3148491dd1bd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77681e209131cea7314b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa767e1e209131cea6d6a7.md>)

Recorded evaluation configuration: {"Model size category":"\<10B"}. This record does not assert independent reproduction.

### GLM-4-9B

BLEU-1: 74.77. Result ID: 699487b03a6c3148491dd1bb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77681e209131cea7314b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74521e209131cea610b6.md>)

Recorded evaluation configuration: {"Model size category":"\<10B"}. This record does not assert independent reproduction.

### Baichuan2-7B-Chat

BLEU-1: 73.46. Result ID: 699487b03a6c3148491dd1be.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77681e209131cea7314b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78081e209131cea766ec.md>)

Recorded evaluation configuration: {"Model size category":"\<10B"}. This record does not assert independent reproduction.

### Yi-1.5-9B-Chat

BLEU-1: 70.31. Result ID: 699487b03a6c3148491dd1ba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77681e209131cea7314b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a71e209131cea6e366.md>)

[Implementation](<https://github.com/01-ai/Yi>)

Recorded evaluation configuration: {"Model size category":"\<10B"}. This record does not assert independent reproduction.

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