# Radiology Report Generation on Wrist (test)

Source: [Radiology Report Generation on Wrist (test)](<https://www.sota2.com/research/sota/radiology-report-generation-on-wrist-test>)

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

Data updated: 2026-02-26T05:36:35.125Z

Evaluation of models generating radiology reports using the test split of the Wrist dataset, assessed using metrics including B4, CIDEr, F1, and Recall.

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 | Radiology Report Generation |
| Dataset (including any stated split) | Wrist (test) |
| Metric | B4 |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [B4](<https://www.sota2.com/research/sota/radiology-report-generation-on-wrist-test.md?metric=B4>): Higher is better; unit: SCALAR.

- [CIDEr](<https://www.sota2.com/research/sota/radiology-report-generation-on-wrist-test.md?metric=CIDEr>): Higher is better; unit: SCALAR.

- [F1](<https://www.sota2.com/research/sota/radiology-report-generation-on-wrist-test.md?metric=F1>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/radiology-report-generation-on-wrist-test.md?metric=Recall>): Higher is better; unit: PERCENT.

## Recorded results

| Method | B4 | Result date | Report paper |
| --- | --- | --- | --- |
| X-RGen | 0.097 | Not recorded | 68fa75261e209131cea6627a |
| X-RGen | 0.089 | Not recorded | 68fa75261e209131cea6627a |
| Transformer | 0.086 | Not recorded | 68fa75261e209131cea6627a |

### X-RGen

B4: 0.097. Result ID: 6993908a3a6c31484916e55f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75261e209131cea6627a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75261e209131cea6627a.md>)

[Implementation](<https://github.com/YtongXie/S4M>)

Recorded evaluation configuration: {"Model category":"generalist","Batch size (bs)":"192"}. This record does not assert independent reproduction.

### X-RGen

B4: 0.089. Result ID: 6993908a3a6c31484916e55e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75261e209131cea6627a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75261e209131cea6627a.md>)

[Implementation](<https://github.com/YtongXie/S4M>)

Recorded evaluation configuration: {"Model category":"specialized","Batch size (bs)":"16"}. This record does not assert independent reproduction.

### Transformer

B4: 0.086. Result ID: 6993908a3a6c31484916e55d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75261e209131cea6627a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703d1e209131cea49db1.md>)

[Implementation](<https://github.com/tensorflow/tensor2tensor>)

Recorded evaluation configuration: {"Model category":"specialized","Batch size (bs)":"16"}. This record does not assert independent reproduction.

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