# Multimodal Question Answering on MM-Vet (test) Source: [Multimodal Question Answering on MM-Vet (test)]() Collection index: [llms.txt]() Data updated: 2026-05-06T09:02:38.962Z Evaluation of model performance on the test split of the MM-Vet dataset for Multimodal Question Answering tasks, measured by 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 | Multimodal Question Answering | | Dataset (including any stated split) | MM-Vet (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 | | --- | --- | --- | --- | | GPT4-V + UnAC | 70.3 | Not recorded | 69facb4ac0f56ed84308a61a | | GPT4-V + SKETCHPAD | 69.3 | Not recorded | 69facb4ac0f56ed84308a61a | | GPT4-V + CCoT | 67.7 | Not recorded | 69facb4ac0f56ed84308a61a | | GPT4-V | 67.2 | Not recorded | 69facb4ac0f56ed84308a61a | | GPT4-V + SoM | 66 | Not recorded | 69facb4ac0f56ed84308a61a | | Gemini-1.5-flash + UnAC | 64.9 | Not recorded | 69facb4ac0f56ed84308a61a | | InternVL2.0-8B + UnAC | 63.3 | Not recorded | 69facb4ac0f56ed84308a61a | | Gemini-1.5-flash | 62.2 | Not recorded | 69facb4ac0f56ed84308a61a | | LLaVA-OneVision-7B + UnAC | 60.2 | Not recorded | 69facb4ac0f56ed84308a61a | | InternVL2.0-8B | 60 | Not recorded | 69facb4ac0f56ed84308a61a | | LLaVA-OneVision-7B | 57.5 | Not recorded | 69facb4ac0f56ed84308a61a | | LLaVA-v1.6-7B + UnAC | 48.5 | Not recorded | 69facb4ac0f56ed84308a61a | | LLaVA-v1.6-7B | 47.5 | Not recorded | 69facb4ac0f56ed84308a61a | ### GPT4-V + UnAC Accuracy: 70.3. Result ID: 69fb03ab47f34ce924de17cd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT4-V","Prompting Strategy":"UnAC"}. This record does not assert independent reproduction. ### GPT4-V + SKETCHPAD Accuracy: 69.3. Result ID: 69fb03ab47f34ce924de17cc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT4-V","Prompting Strategy":"SKETCHPAD"}. This record does not assert independent reproduction. ### GPT4-V + CCoT Accuracy: 67.7. Result ID: 69fb03ab47f34ce924de17cb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT4-V","Prompting Strategy":"CCoT"}. This record does not assert independent reproduction. ### GPT4-V Accuracy: 67.2. Result ID: 69fb03ab47f34ce924de17c9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT4-V","Prompting Strategy":"Baseline"}. This record does not assert independent reproduction. ### GPT4-V + SoM Accuracy: 66. Result ID: 69fb03ab47f34ce924de17ca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT4-V","Prompting Strategy":"SoM"}. This record does not assert independent reproduction. ### Gemini-1.5-flash + UnAC Accuracy: 64.9. Result ID: 69fb03ab47f34ce924de17c6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Gemini-1.5-flash","Prompting Strategy":"UnAC"}. This record does not assert independent reproduction. ### InternVL2.0-8B + UnAC Accuracy: 63.3. Result ID: 69fb03ab47f34ce924de17c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"InternVL2.0-8B","Prompting Strategy":"UnAC"}. This record does not assert independent reproduction. ### Gemini-1.5-flash Accuracy: 62.2. Result ID: 69fb03ab47f34ce924de17c5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Gemini-1.5-flash","Prompting Strategy":"Baseline"}. This record does not assert independent reproduction. ### LLaVA-OneVision-7B + UnAC Accuracy: 60.2. Result ID: 69fb03ab47f34ce924de17c4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-OneVision-7B","Prompting Strategy":"UnAC"}. This record does not assert independent reproduction. ### InternVL2.0-8B Accuracy: 60. Result ID: 69fb03ab47f34ce924de17c7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"InternVL2.0-8B","Prompting Strategy":"Baseline"}. This record does not assert independent reproduction. ### LLaVA-OneVision-7B Accuracy: 57.5. Result ID: 69fb03ab47f34ce924de17c3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"LLaVA-OneVision-7B","Prompting Strategy":"Baseline"}. This record does not assert independent reproduction. ### LLaVA-v1.6-7B + UnAC Accuracy: 48.5. Result ID: 69fb03ab47f34ce924de17c2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-v1.6-7B","Prompting Strategy":"UnAC"}. This record does not assert independent reproduction. ### LLaVA-v1.6-7B Accuracy: 47.5. Result ID: 69fb03ab47f34ce924de17c1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"LLaVA-v1.6-7B","Prompting Strategy":"Baseline"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.