# Medical Report Generation on SpineBench Source: [Medical Report Generation on SpineBench]() Collection index: [llms.txt]() Data updated: 2026-03-06T08:43:50.547Z Evaluation of models generating medical reports based on the SpineBench dataset, assessed using metrics such as SIP, AAD, TR, RPM, RD, Sum, and Overall Average. 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 | Medical Report Generation | | Dataset (including any stated split) | SpineBench | | Metric | SIP | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [SIP](): Higher is better; unit: SCALAR. - [AAD](): Higher is better; unit: SCALAR. - [TR](): Higher is better; unit: SCALAR. - [RPM](): Higher is better; unit: SCALAR. - [RD](): Higher is better; unit: SCALAR. - [Sum Score](): Higher is better; unit: SCALAR. - [Overall Average Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | SIP | Result date | Report paper | | --- | --- | --- | --- | | Gemini-2.5-Pro | 4.55 | Not recorded | 68fa7be61e209131cea8b2e6 | | GPT5-mini | 4.55 | Not recorded | 68fa7be61e209131cea8b2e6 | | GPT5 | 4.54 | Not recorded | 68fa7be61e209131cea8b2e6 | | Gemini-2.5-Flash | 4.43 | Not recorded | 68fa7be61e209131cea8b2e6 | | O3 | 4.39 | Not recorded | 68fa7be61e209131cea8b2e6 | | SpineGPT | 4.15 | Not recorded | 68fa7be61e209131cea8b2e6 | | Claude4 | 3.96 | Not recorded | 68fa7be61e209131cea8b2e6 | | GLM-4.5V | 3.85 | Not recorded | 68fa7be61e209131cea8b2e6 | | GPT-4o | 3.16 | Not recorded | 68fa7be61e209131cea8b2e6 | | Qwen2.5-VL-72B | 3.14 | Not recorded | 68fa7be61e209131cea8b2e6 | | Linshu-32B | 3.05 | Not recorded | 68fa7be61e209131cea8b2e6 | | Medgemma-27B | 2.88 | Not recorded | 68fa7be61e209131cea8b2e6 | | HuatuoGPT-7B | 2.42 | Not recorded | 68fa7be61e209131cea8b2e6 | | Qwen2.5VL-7B | 2.27 | Not recorded | 68fa7be61e209131cea8b2e6 | ### Gemini-2.5-Pro SIP: 4.55. Result ID: 69aa93bf6dbb7075b954660e. [Reporting paper]() Recorded evaluation configuration: {"Size":"-"}. This record does not assert independent reproduction. ### GPT5-mini SIP: 4.55. Result ID: 69aa93bf6dbb7075b9546611. [Reporting paper]() Recorded evaluation configuration: {"Size":"-"}. This record does not assert independent reproduction. ### GPT5 SIP: 4.54. Result ID: 69aa93bf6dbb7075b954660c. [Reporting paper]() Recorded evaluation configuration: {"Size":"-"}. This record does not assert independent reproduction. ### Gemini-2.5-Flash SIP: 4.43. Result ID: 69aa93bf6dbb7075b9546612. [Reporting paper]() Recorded evaluation configuration: {"Size":"-"}. This record does not assert independent reproduction. ### O3 SIP: 4.39. Result ID: 69aa93bf6dbb7075b954660d. [Reporting paper]() Recorded evaluation configuration: {"Size":"-"}. This record does not assert independent reproduction. ### SpineGPT SIP: 4.15. Result ID: 69aa93bf6dbb7075b9546619. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### Claude4 SIP: 3.96. Result ID: 69aa93bf6dbb7075b954660f. [Reporting paper]() Recorded evaluation configuration: {"Size":"-"}. This record does not assert independent reproduction. ### GLM-4.5V SIP: 3.85. Result ID: 69aa93bf6dbb7075b9546613. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"21B"}. This record does not assert independent reproduction. ### GPT-4o SIP: 3.16. Result ID: 69aa93bf6dbb7075b9546610. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"-"}. This record does not assert independent reproduction. ### Qwen2.5-VL-72B SIP: 3.14. Result ID: 69aa93bf6dbb7075b9546614. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"72B"}. This record does not assert independent reproduction. ### Linshu-32B SIP: 3.05. Result ID: 69aa93bf6dbb7075b9546615. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"32B"}. This record does not assert independent reproduction. ### Medgemma-27B SIP: 2.88. Result ID: 69aa93bf6dbb7075b9546616. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"27B"}. This record does not assert independent reproduction. ### HuatuoGPT-7B SIP: 2.42. Result ID: 69aa93bf6dbb7075b9546617. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### Qwen2.5VL-7B SIP: 2.27. Result ID: 69aa93bf6dbb7075b9546618. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.