# Medical Vision-Language Modeling on CT-FlowBench Source: [Medical Vision-Language Modeling on CT-FlowBench]() Collection index: [llms.txt]() Data updated: 2026-03-04T09:04:17.288Z Evaluation of Medical Vision-Language Modeling performance on the CT-FlowBench dataset, typically measured using QA, AM, and DD scores. 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 Vision-Language Modeling | | Dataset (including any stated split) | CT-FlowBench | | Metric | QA Score | | 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 - [QA Score](): Higher is better; unit: PERCENT. - [AM Score](): Higher is better; unit: PERCENT. - [DD Score](): Higher is better; unit: PERCENT. - [Average Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | QA Score | Result date | Report paper | | --- | --- | --- | --- | | Hulu-Med-7B | 58 | Not recorded | 69a66bdd2d603e6de3e3ccb2 | | Gemini-3-Pro-Preview | 45 | Not recorded | 69a66bdd2d603e6de3e3ccb2 | | Claude-Sonnet-4.5 | 44 | Not recorded | 69a66bdd2d603e6de3e3ccb2 | | CT-Flow-7B | 43 | Not recorded | 69a66bdd2d603e6de3e3ccb2 | | CT-Flow-8B | 42 | Not recorded | 69a66bdd2d603e6de3e3ccb2 | | M3D-RAD | 39 | Not recorded | 69a66bdd2d603e6de3e3ccb2 | | GPT-5.2 | 35 | Not recorded | 69a66bdd2d603e6de3e3ccb2 | | Qwen3-VL-235B-A22B-Instruct | 30 | Not recorded | 69a66bdd2d603e6de3e3ccb2 | | Qwen3-VL-8B-Instruct | 30 | Not recorded | 69a66bdd2d603e6de3e3ccb2 | | GLM4.6-V | 25 | Not recorded | 69a66bdd2d603e6de3e3ccb2 | | M3D-LaMed-Llama-2-7B | 17 | Not recorded | 69a66bdd2d603e6de3e3ccb2 | | Qwen2.5-VL-7B-Instruct | 14 | Not recorded | 69a66bdd2d603e6de3e3ccb2 | ### Hulu-Med-7B QA Score: 58. Result ID: 69a7f4a96dbb7075b94cf3fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tool-use":"false"}. This record does not assert independent reproduction. ### Gemini-3-Pro-Preview QA Score: 45. Result ID: 69a7f4a96dbb7075b94cf3f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tool-use":"true"}. This record does not assert independent reproduction. ### Claude-Sonnet-4.5 QA Score: 44. Result ID: 69a7f4a96dbb7075b94cf3f7. [Reporting paper]() Recorded evaluation configuration: {"Tool-use":"true"}. This record does not assert independent reproduction. ### CT-Flow-7B QA Score: 43. Result ID: 69a7f4a96dbb7075b94cf3ff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tool-use":"true"}. This record does not assert independent reproduction. ### CT-Flow-8B QA Score: 42. Result ID: 69a7f4a96dbb7075b94cf400. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tool-use":"true"}. This record does not assert independent reproduction. ### M3D-RAD QA Score: 39. Result ID: 69a7f4a96dbb7075b94cf3fb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tool-use":"false"}. This record does not assert independent reproduction. ### GPT-5.2 QA Score: 35. Result ID: 69a7f4a96dbb7075b94cf3f5. [Reporting paper]() Recorded evaluation configuration: {"Tool-use":"true"}. This record does not assert independent reproduction. ### Qwen3-VL-235B-A22B-Instruct QA Score: 30. Result ID: 69a7f4a96dbb7075b94cf3f8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tool-use":"true"}. This record does not assert independent reproduction. ### Qwen3-VL-8B-Instruct QA Score: 30. Result ID: 69a7f4a96dbb7075b94cf3fe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tool-use":"true"}. This record does not assert independent reproduction. ### GLM4.6-V QA Score: 25. Result ID: 69a7f4a96dbb7075b94cf3f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tool-use":"true"}. This record does not assert independent reproduction. ### M3D-LaMed-Llama-2-7B QA Score: 17. Result ID: 69a7f4a96dbb7075b94cf3fa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tool-use":"false"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B-Instruct QA Score: 14. Result ID: 69a7f4a96dbb7075b94cf3fd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tool-use":"true"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.