# Radiology Report Generation on IU-Xray Findings generation v1.5 (Vicuna-7B) Source: [Radiology Report Generation on IU-Xray Findings generation v1.5 (Vicuna-7B)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:00:44.106Z Evaluation of radiology report generation models using the specific v1.5 findings dataset context (Vicuna-7B), assessed using ROUGE-L, BLEU-4, RG\_ER, and Macro-F1-14 metrics. 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) | IU-Xray Findings generation v1.5 (Vicuna-7B) | | Metric | ROUGE-L | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [ROUGE-L](): Higher is better; unit: PERCENT. - [BLEU-4](): Higher is better; unit: PERCENT. - [RG\_ER](): Lower is better; unit: PERCENT. - [Macro-F1-14](): Higher is better; unit: PERCENT. ## Recorded results | Method | ROUGE-L | Result date | Report paper | | --- | --- | --- | --- | | RadJEPA | 28.4 | Not recorded | 6973007cb2be0ed85a78c9d3 | | RadJEPAcontrol | 27.1 | Not recorded | 6973007cb2be0ed85a78c9d3 | | I-JEPA | 26.7 | Not recorded | 6973007cb2be0ed85a78c9d3 | | BioViL | 26.3 | Not recorded | 6973007cb2be0ed85a78c9d3 | | RAD-DINO | 26.3 | Not recorded | 6973007cb2be0ed85a78c9d3 | | RAD-DINO | 25.8 | Not recorded | 6973007cb2be0ed85a78c9d3 | | CheXzero | 25.6 | Not recorded | 6973007cb2be0ed85a78c9d3 | | RAD-DINOcontrol | 25.5 | Not recorded | 6973007cb2be0ed85a78c9d3 | | CLIP@224 | 25.4 | Not recorded | 6973007cb2be0ed85a78c9d3 | | DINO-v2 | 25.4 | Not recorded | 6973007cb2be0ed85a78c9d3 | | CLIP@336 | 25.3 | Not recorded | 6973007cb2be0ed85a78c9d3 | | BiomedCLIP | 20.2 | Not recorded | 6973007cb2be0ed85a78c9d3 | ### RadJEPA ROUGE-L: 28.4. Result ID: 69979a185698665ec4efde9d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input resolution":"224x224","# Tokens":1369}. This record does not assert independent reproduction. ### RadJEPAcontrol ROUGE-L: 27.1. Result ID: 69979a185698665ec4efde9c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input resolution":"224x224","# Tokens":1369}. This record does not assert independent reproduction. ### I-JEPA ROUGE-L: 26.7. Result ID: 69979a185698665ec4efde9b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input resolution":"224x224","# Tokens":1369}. This record does not assert independent reproduction. ### BioViL ROUGE-L: 26.3. Result ID: 69979a185698665ec4efde97. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input resolution":"512x512","# Tokens":196}. This record does not assert independent reproduction. ### RAD-DINO ROUGE-L: 26.3. Result ID: 69979a185698665ec4efde9a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input resolution":"518x518","# Tokens":1369,"reproduced":true}. This record does not assert independent reproduction. ### RAD-DINO ROUGE-L: 25.8. Result ID: 69979a185698665ec4efde99. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input resolution":"518x518","# Tokens":1369}. This record does not assert independent reproduction. ### CheXzero ROUGE-L: 25.6. Result ID: 69979a185698665ec4efde96. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input resolution":"224x224","# Tokens":49}. This record does not assert independent reproduction. ### RAD-DINOcontrol ROUGE-L: 25.5. Result ID: 69979a185698665ec4efde98. [Reporting paper]() Recorded evaluation configuration: {"Input resolution":"518x518","# Tokens":1369}. This record does not assert independent reproduction. ### CLIP@224 ROUGE-L: 25.4. Result ID: 69979a185698665ec4efde92. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input resolution":"224x224","# Tokens":256}. This record does not assert independent reproduction. ### DINO-v2 ROUGE-L: 25.4. Result ID: 69979a185698665ec4efde94. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input resolution":"518x518","# Tokens":1369}. This record does not assert independent reproduction. ### CLIP@336 ROUGE-L: 25.3. Result ID: 69979a185698665ec4efde93. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input resolution":"316x316","# Tokens":576}. This record does not assert independent reproduction. ### BiomedCLIP ROUGE-L: 20.2. Result ID: 69979a185698665ec4efde95. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input resolution":"224x224","# Tokens":256}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.