# Close-Ended QA on SpineBench Source: [Close-Ended QA on SpineBench]() Collection index: [llms.txt]() Data updated: 2026-03-06T08:43:50.516Z Evaluation of Close-Ended Question Answering performance on the SpineBench dataset, covering text, image, and overall 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 | Close-Ended QA | | Dataset (including any stated split) | SpineBench | | Metric | Accuracy (Text) | | Unit | PERCENT | | 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 - [Accuracy (Text)](): Higher is better; unit: PERCENT. - [Accuracy (Image)](): Higher is better; unit: PERCENT. - [Average Accuracy](): Higher is better; unit: PERCENT. - [Overall Average Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Text) | Result date | Report paper | | --- | --- | --- | --- | | SpineGPT | 89.46 | Not recorded | 68fa7be61e209131cea8b2e6 | | GPT5-mini | 89.12 | Not recorded | 68fa7be61e209131cea8b2e6 | | Gemini-2.5-Pro | 88.44 | Not recorded | 68fa7be61e209131cea8b2e6 | | GPT5 | 87.41 | Not recorded | 68fa7be61e209131cea8b2e6 | | O3 | 86.73 | Not recorded | 68fa7be61e209131cea8b2e6 | | GPT-4o | 86.73 | Not recorded | 68fa7be61e209131cea8b2e6 | | GLM-4.5V | 85.71 | Not recorded | 68fa7be61e209131cea8b2e6 | | Qwen2.5-VL-72B | 84.69 | Not recorded | 68fa7be61e209131cea8b2e6 | | Gemini-2.5-Flash | 83.67 | Not recorded | 68fa7be61e209131cea8b2e6 | | Medgemma-27B | 83.33 | Not recorded | 68fa7be61e209131cea8b2e6 | | Linshu-32B | 81.29 | Not recorded | 68fa7be61e209131cea8b2e6 | | Claude4 | 79.59 | Not recorded | 68fa7be61e209131cea8b2e6 | | HuatuoGPT-7B | 75.85 | Not recorded | 68fa7be61e209131cea8b2e6 | | Qwen2.5VL-7B | 75.51 | Not recorded | 68fa7be61e209131cea8b2e6 | ### SpineGPT Accuracy (Text): 89.46. Result ID: 69aa93bf6dbb7075b954660b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### GPT5-mini Accuracy (Text): 89.12. Result ID: 69aa93bf6dbb7075b9546603. [Reporting paper]() Recorded evaluation configuration: {"Size":"-"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro Accuracy (Text): 88.44. Result ID: 69aa93bf6dbb7075b9546600. [Reporting paper]() Recorded evaluation configuration: {"Size":"-"}. This record does not assert independent reproduction. ### GPT5 Accuracy (Text): 87.41. Result ID: 69aa93bf6dbb7075b95465fe. [Reporting paper]() Recorded evaluation configuration: {"Size":"-"}. This record does not assert independent reproduction. ### O3 Accuracy (Text): 86.73. Result ID: 69aa93bf6dbb7075b95465ff. [Reporting paper]() Recorded evaluation configuration: {"Size":"-"}. This record does not assert independent reproduction. ### GPT-4o Accuracy (Text): 86.73. Result ID: 69aa93bf6dbb7075b9546602. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"-"}. This record does not assert independent reproduction. ### GLM-4.5V Accuracy (Text): 85.71. Result ID: 69aa93bf6dbb7075b9546605. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"21B"}. This record does not assert independent reproduction. ### Qwen2.5-VL-72B Accuracy (Text): 84.69. Result ID: 69aa93bf6dbb7075b9546606. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"72B"}. This record does not assert independent reproduction. ### Gemini-2.5-Flash Accuracy (Text): 83.67. Result ID: 69aa93bf6dbb7075b9546604. [Reporting paper]() Recorded evaluation configuration: {"Size":"-"}. This record does not assert independent reproduction. ### Medgemma-27B Accuracy (Text): 83.33. Result ID: 69aa93bf6dbb7075b9546608. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"27B"}. This record does not assert independent reproduction. ### Linshu-32B Accuracy (Text): 81.29. Result ID: 69aa93bf6dbb7075b9546607. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"32B"}. This record does not assert independent reproduction. ### Claude4 Accuracy (Text): 79.59. Result ID: 69aa93bf6dbb7075b9546601. [Reporting paper]() Recorded evaluation configuration: {"Size":"-"}. This record does not assert independent reproduction. ### HuatuoGPT-7B Accuracy (Text): 75.85. Result ID: 69aa93bf6dbb7075b9546609. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### Qwen2.5VL-7B Accuracy (Text): 75.51. Result ID: 69aa93bf6dbb7075b954660a. [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.