# Visual Question Answering on ScienceQA full Source: [Visual Question Answering on ScienceQA full]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:29:37.134Z Evaluation of model performance on the full ScienceQA dataset for visual question answering capabilities, typically measured 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 | Visual Question Answering | | Dataset (including any stated split) | ScienceQA full | | Metric | Accuracy | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | LLaVA-Next 13B | 75.85 | Not recorded | 68fa72d01e209131cea58a8a | | LLaVA-v1.5 13B | 74.96 | Not recorded | 68fa72d01e209131cea58a8a | | OmniFusion | 74.13 | Not recorded | 68fa72d01e209131cea58a8a | | LLaVA-Next 7B | 73.21 | Not recorded | 68fa72d01e209131cea58a8a | | OmniFusion | 73.21 | Not recorded | 68fa72d01e209131cea58a8a | | OmniFusion | 71.26 | Not recorded | 68fa72d01e209131cea58a8a | | OmniFusion | 71.21 | Not recorded | 68fa72d01e209131cea58a8a | | OmniFusion | 71.09 | Not recorded | 68fa72d01e209131cea58a8a | | LLaVA-v1.5 7B | 70.41 | Not recorded | 68fa72d01e209131cea58a8a | | OmniFusion | 70.3 | Not recorded | 68fa72d01e209131cea58a8a | ### LLaVA-Next 13B Accuracy: 75.85. Result ID: 699298b63a6c31484910092f. [Reporting paper]() Recorded evaluation configuration: {"LLM":"Vicuna-13B","Encoder":"CLIP VIT-large/14","Resolution":"672","Zero-shot":"true"}. This record does not assert independent reproduction. ### LLaVA-v1.5 13B Accuracy: 74.96. Result ID: 699298b63a6c314849100927. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM":"Vicuna-13B","Encoder":"CLIP VIT-large/14","Resolution":"336","Zero-shot":"true"}. This record does not assert independent reproduction. ### OmniFusion Accuracy: 74.13. Result ID: 699298b63a6c31484910092a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM":"GigaChat-7B","Encoder":"InternViT-6B-448px V1-2","Resolution":"448","Zero-shot":"true"}. This record does not assert independent reproduction. ### LLaVA-Next 7B Accuracy: 73.21. Result ID: 699298b63a6c31484910092e. [Reporting paper]() Recorded evaluation configuration: {"LLM":"Vicuna-7B","Encoder":"CLIP VIT-large/14","Resolution":"672","Zero-shot":"true"}. This record does not assert independent reproduction. ### OmniFusion Accuracy: 73.21. Result ID: 699298b63a6c314849100930. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM":"GigaChat-7B","Encoder":"CLIP VIT-large/14 + grid-split","Resolution":"672","Zero-shot":"true"}. This record does not assert independent reproduction. ### OmniFusion Accuracy: 71.26. Result ID: 699298b63a6c31484910092d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM":"Vicuna-7B","Encoder":"CLIP VIT-large/14 + DinoV2","Resolution":"336","Zero-shot":"true"}. This record does not assert independent reproduction. ### OmniFusion Accuracy: 71.21. Result ID: 699298b63a6c314849100929. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM":"GigaChat-7B","Encoder":"CLIP VIT-large/14","Resolution":"336","Zero-shot":"true"}. This record does not assert independent reproduction. ### OmniFusion Accuracy: 71.09. Result ID: 699298b63a6c31484910092b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM":"GigaChat-7B","Encoder":"CLIP VIT-large/14 + DinoV2","Resolution":"336","Zero-shot":"true"}. This record does not assert independent reproduction. ### LLaVA-v1.5 7B Accuracy: 70.41. Result ID: 699298b63a6c314849100928. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM":"Vicuna-7B","Encoder":"CLIP VIT-large/14","Resolution":"336","Zero-shot":"true"}. This record does not assert independent reproduction. ### OmniFusion Accuracy: 70.3. Result ID: 699298b63a6c31484910092c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LLM":"Mistral-7B","Encoder":"CLIP VIT-large/14 + DinoV2","Resolution":"336","Zero-shot":"true"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.