# Clinical Case Generation on Held-out (test)

Source: [Clinical Case Generation on Held-out (test)](<https://www.sota2.com/research/sota/clinical-case-generation-on-held-out-test>)

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

Data updated: 2026-03-10T13:00:55.743Z

Evaluation of models performing clinical case generation using the held-out test split, assessed using text generation metrics (BLEU, ROUGE) and entity extraction accuracy (Entity-F1).

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 | Clinical case generation |
| Dataset (including any stated split) | Held-out (test) |
| Metric | BLEU-4 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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-4](<https://www.sota2.com/research/sota/clinical-case-generation-on-held-out-test.md?metric=BLEU-4>): Higher is better; unit: PERCENT.

- [ROUGE-L](<https://www.sota2.com/research/sota/clinical-case-generation-on-held-out-test.md?metric=ROUGE-L>): Higher is better; unit: PERCENT.

- [Entity-F1](<https://www.sota2.com/research/sota/clinical-case-generation-on-held-out-test.md?metric=Entity-F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | BLEU-4 | Result date | Report paper |
| --- | --- | --- | --- |
| CORE-Acu | 18.98 | Not recorded | 69afa5bc2d603e6de3e43ec1 |
| Qwen-Max | 8.65 | Not recorded | 69afa5bc2d603e6de3e43ec1 |
| Qwen3-8B | 8.14 | Not recorded | 69afa5bc2d603e6de3e43ec1 |
| GPT-4o | 7.22 | Not recorded | 69afa5bc2d603e6de3e43ec1 |
| GLM-4.6 | 6.97 | Not recorded | 69afa5bc2d603e6de3e43ec1 |
| HuatuoGPT-o1-7B | 0.59 | Not recorded | 69afa5bc2d603e6de3e43ec1 |

### CORE-Acu

BLEU-4: 18.98. Result ID: 69b015f16dbb7075b95a1ab6.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bc2d603e6de3e43ec1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69afa5bc2d603e6de3e43ec1.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Qwen-Max

BLEU-4: 8.65. Result ID: 69b015f16dbb7075b95a1aba.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bc2d603e6de3e43ec1.md>)

Recorded evaluation configuration: {"variant":"General"}. This record does not assert independent reproduction.

### Qwen3-8B

BLEU-4: 8.14. Result ID: 69b015f16dbb7075b95a1ab9.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bc2d603e6de3e43ec1.md>)

Recorded evaluation configuration: {"variant":"Base"}. This record does not assert independent reproduction.

### GPT-4o

BLEU-4: 7.22. Result ID: 69b015f16dbb7075b95a1abb.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bc2d603e6de3e43ec1.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GLM-4.6

BLEU-4: 6.97. Result ID: 69b015f16dbb7075b95a1ab7.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bc2d603e6de3e43ec1.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### HuatuoGPT-o1-7B

BLEU-4: 0.59. Result ID: 69b015f16dbb7075b95a1ab8.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5bc2d603e6de3e43ec1.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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