# Report Generation on MIMIC-CXR Exp. (test)

Source: [Report Generation on MIMIC-CXR Exp. (test)](<https://www.sota2.com/research/sota/report-generation-on-mimic-cxr-exp-test>)

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

Data updated: 2026-02-26T05:37:18.496Z

Evaluation of models generating medical reports from the experimental test split of the MIMIC-CXR dataset, measured using text generation metrics like BLEU 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 | Report Generation |
| Dataset (including any stated split) | MIMIC-CXR Exp. (test) |
| Metric | BLEU-4 |
| Unit | SCALAR |
| 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/report-generation-on-mimic-cxr-exp-test.md?metric=BLEU-4>): Higher is better; unit: SCALAR.

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

## Recorded results

| Method | BLEU-4 | Result date | Report paper |
| --- | --- | --- | --- |
| VILA-M3 | 21.6 | Not recorded | 68fa773a1e209131cea71cf8 |
| VILA-M3 | 21.6 | Not recorded | 68fa773a1e209131cea71cf8 |
| VILA-M3 | 21.1 | Not recorded | 68fa773a1e209131cea71cf8 |
| Med-Gemini | 20.5 | Not recorded | 68fa773a1e209131cea71cf8 |
| VILA-M3 | 20.2 | Not recorded | 68fa773a1e209131cea71cf8 |
| Task Spfc. SOTA | 15.4 | Not recorded | 68fa773a1e209131cea71cf8 |

### VILA-M3

BLEU-4: 21.6. Result ID: 69946e8d3a6c3148491d33b9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71cf8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71cf8.md>)

Recorded evaluation configuration: {"Number of Parameters":"13B"}. This record does not assert independent reproduction.

### VILA-M3

BLEU-4: 21.6. Result ID: 69946e8d3a6c3148491d33ba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71cf8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71cf8.md>)

Recorded evaluation configuration: {"Number of Parameters":"40B"}. This record does not assert independent reproduction.

### VILA-M3

BLEU-4: 21.1. Result ID: 69946e8d3a6c3148491d33b8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71cf8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71cf8.md>)

Recorded evaluation configuration: {"Number of Parameters":"8B"}. This record does not assert independent reproduction.

### Med-Gemini

BLEU-4: 20.5. Result ID: 69946e8d3a6c3148491d33b5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71cf8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73141e209131cea5a5c0.md>)

Recorded evaluation configuration: {"Number of Parameters":"1.5T"}. This record does not assert independent reproduction.

### VILA-M3

BLEU-4: 20.2. Result ID: 69946e8d3a6c3148491d33b7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71cf8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71cf8.md>)

Recorded evaluation configuration: {"Number of Parameters":"3B"}. This record does not assert independent reproduction.

### Task Spfc. SOTA

BLEU-4: 15.4. Result ID: 69946e8d3a6c3148491d33b6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71cf8.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.