# Text-only Question Answering on MedXpertQA text Source: [Text-only Question Answering on MedXpertQA text]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:31:38.251Z Evaluation of model performance on the text-only subset of the MedXpertQA dataset using accuracy. 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 | Text-only Question Answering | | Dataset (including any stated split) | MedXpertQA text | | Metric | Accuracy | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | o1 | 48.9 | Not recorded | 6965d19b6343fa78c83236bd | | PulseMind-72B | 29.8 | Not recorded | 6965d19b6343fa78c83236bd | | Gemini2.5-pro | 24.3 | Not recorded | 6965d19b6343fa78c83236bd | | Lingshu-32B | 22.7 | Not recorded | 6965d19b6343fa78c83236bd | | GPT-4o | 22.5 | Not recorded | 6965d19b6343fa78c83236bd | | PulseMind-32B | 21.5 | Not recorded | 6965d19b6343fa78c83236bd | | InternVL3-78B | 18.5 | Not recorded | 6965d19b6343fa78c83236bd | | Qwen2.5VL-72B | 16.1 | Not recorded | 6965d19b6343fa78c83236bd | | InternVL3-38B | 16 | Not recorded | 6965d19b6343fa78c83236bd | | HuatuoGPT-vision-34B | 16 | Not recorded | 6965d19b6343fa78c83236bd | | Qwen2.5VL-32B | 15.6 | Not recorded | 6965d19b6343fa78c83236bd | | LLAVA-med-34B | 14.1 | Not recorded | 6965d19b6343fa78c83236bd | ### o1 Accuracy: 48.9. Result ID: 6997ca645698665ec4217483. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Proprietary"}. This record does not assert independent reproduction. ### PulseMind-72B Accuracy: 29.8. Result ID: 6997ca645698665ec4217487. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Open-source","Model Scale":"~72B"}. This record does not assert independent reproduction. ### Gemini2.5-pro Accuracy: 24.3. Result ID: 6997ca645698665ec4217484. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Proprietary"}. This record does not assert independent reproduction. ### Lingshu-32B Accuracy: 22.7. Result ID: 6997ca645698665ec421748c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Open-source","Model Scale":"~32B"}. This record does not assert independent reproduction. ### GPT-4o Accuracy: 22.5. Result ID: 6997ca645698665ec4217482. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Proprietary"}. This record does not assert independent reproduction. ### PulseMind-32B Accuracy: 21.5. Result ID: 6997ca645698665ec421748d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Open-source","Model Scale":"~32B"}. This record does not assert independent reproduction. ### InternVL3-78B Accuracy: 18.5. Result ID: 6997ca645698665ec4217485. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Open-source","Model Scale":"~72B"}. This record does not assert independent reproduction. ### Qwen2.5VL-72B Accuracy: 16.1. Result ID: 6997ca645698665ec4217486. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Open-source","Model Scale":"~72B"}. This record does not assert independent reproduction. ### InternVL3-38B Accuracy: 16. Result ID: 6997ca645698665ec4217488. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Open-source","Model Scale":"~32B"}. This record does not assert independent reproduction. ### HuatuoGPT-vision-34B Accuracy: 16. Result ID: 6997ca645698665ec421748b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Open-source","Model Scale":"~32B"}. This record does not assert independent reproduction. ### Qwen2.5VL-32B Accuracy: 15.6. Result ID: 6997ca645698665ec4217489. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Open-source","Model Scale":"~32B"}. This record does not assert independent reproduction. ### LLAVA-med-34B Accuracy: 14.1. Result ID: 6997ca645698665ec421748a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Open-source","Model Scale":"~32B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.