# Text Multiple Choice Question Answering on MC-LLaVA Source: [Text Multiple Choice Question Answering on MC-LLaVA]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:39:08.298Z Evaluation of model performance on the MC-LLaVA dataset for Text Multiple Choice Question Answering, measured using Choice-T Accuracy variants (Single, Multi, Weight). 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 Multiple Choice Question Answering | | Dataset (including any stated split) | MC-LLaVA | | Metric | Choice-T Accuracy (Single) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 - [Choice-T Accuracy (Single)](): Higher is better; unit: PERCENT. - [Choice-T Accuracy (Multi)](): Higher is better; unit: PERCENT. - [Choice-T Accuracy (Weight)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Choice-T Accuracy (Single) | Result date | Report paper | | --- | --- | --- | --- | | MC-LLaVA | 72.9 | Not recorded | 68fa77a01e209131cea7475f | | MC-LLaVA | 72.3 | Not recorded | 68fa77a01e209131cea7475f | | GPT4o+Prompt | 71.2 | Not recorded | 68fa77a01e209131cea7475f | | PeKit | 71.2 | Not recorded | 68fa77a01e209131cea7475f | | RAP-MLLM | 70.9 | Not recorded | 68fa77a01e209131cea7475f | | Yo'LLaVA-S | 70.3 | Not recorded | 68fa77a01e209131cea7475f | | Yo'LLaVA-M | 68.4 | Not recorded | 68fa77a01e209131cea7475f | | LLaVA+Prompt | 64.6 | Not recorded | 68fa77a01e209131cea7475f | | LLaVA+Prompt | 59.7 | Not recorded | 68fa77a01e209131cea7475f | | LLaVA | 41.1 | Not recorded | 68fa77a01e209131cea7475f | ### MC-LLaVA Choice-T Accuracy (Single): 72.9. Result ID: 699af2885698665ec483b2f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"T (Tokens)":"10^1","Auxiliary Loss":true}. This record does not assert independent reproduction. ### MC-LLaVA Choice-T Accuracy (Single): 72.3. Result ID: 699af2885698665ec483b2f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"T (Tokens)":"10^1","Auxiliary Loss":false}. This record does not assert independent reproduction. ### GPT4o+Prompt Choice-T Accuracy (Single): 71.2. Result ID: 699af2885698665ec483b2e8. [Reporting paper]() Recorded evaluation configuration: {"T (Tokens)":"10^1"}. This record does not assert independent reproduction. ### PeKit Choice-T Accuracy (Single): 71.2. Result ID: 699af2885698665ec483b2ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"T (Tokens)":"0"}. This record does not assert independent reproduction. ### RAP-MLLM Choice-T Accuracy (Single): 70.9. Result ID: 699af2885698665ec483b2ee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"T (Tokens)":"10^2"}. This record does not assert independent reproduction. ### Yo'LLaVA-S Choice-T Accuracy (Single): 70.3. Result ID: 699af2885698665ec483b2ec. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"T (Tokens)":"10^1"}. This record does not assert independent reproduction. ### Yo'LLaVA-M Choice-T Accuracy (Single): 68.4. Result ID: 699af2885698665ec483b2ed. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"T (Tokens)":"10^1"}. This record does not assert independent reproduction. ### LLaVA+Prompt Choice-T Accuracy (Single): 64.6. Result ID: 699af2885698665ec483b2eb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"T (Tokens)":"10^2"}. This record does not assert independent reproduction. ### LLaVA+Prompt Choice-T Accuracy (Single): 59.7. Result ID: 699af2885698665ec483b2ea. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"T (Tokens)":"10^1"}. This record does not assert independent reproduction. ### LLaVA Choice-T Accuracy (Single): 41.1. Result ID: 699af2885698665ec483b2e9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"T (Tokens)":"0"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.