# 3D/4D Video Question Answering on VLM4D real Source: [3D/4D Video Question Answering on VLM4D real]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:31:49.726Z Evaluation of model performance on the VLM4D real dataset for 3D/4D Video Question Answering, 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 | 3D/4D Video Question Answering | | Dataset (including any stated split) | VLM4D real | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 | | --- | --- | --- | --- | | Gemini-2.5-Pro | 63.5 | Not recorded | 6948d086423ea42265729f78 | | GPT-4o | 60 | Not recorded | 6948d086423ea42265729f78 | | 4D-RGPT-8B | 52.7 | Not recorded | 6948d086423ea42265729f78 | | SpaceR-7B | 51.3 | Not recorded | 6948d086423ea42265729f78 | | ViLaSR-7B | 46.9 | Not recorded | 6948d086423ea42265729f78 | | VideoLLaMA3-7B | 46.5 | Not recorded | 6948d086423ea42265729f78 | | NVILA-Lite-8B | 46.5 | Not recorded | 6948d086423ea42265729f78 | | SpatialReasoner-7B | 43.4 | Not recorded | 6948d086423ea42265729f78 | | Qwen2.5-VL-7B | 43.3 | Not recorded | 6948d086423ea42265729f78 | | InternVL2.5-8B | 42.4 | Not recorded | 6948d086423ea42265729f78 | | LLaVA-OneVision-7B | 36 | Not recorded | 6948d086423ea42265729f78 | ### Gemini-2.5-Pro Accuracy: 63.5. Result ID: 69982c705698665ec487664b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-4o Accuracy: 60. Result ID: 69982c705698665ec487664a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### 4D-RGPT-8B Accuracy: 52.7. Result ID: 69982c705698665ec4876654. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"parameters":"8B"}. This record does not assert independent reproduction. ### SpaceR-7B Accuracy: 51.3. Result ID: 69982c705698665ec4876652. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"parameters":"7B"}. This record does not assert independent reproduction. ### ViLaSR-7B Accuracy: 46.9. Result ID: 69982c705698665ec4876650. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"parameters":"7B"}. This record does not assert independent reproduction. ### VideoLLaMA3-7B Accuracy: 46.5. Result ID: 69982c705698665ec487664e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"parameters":"7B"}. This record does not assert independent reproduction. ### NVILA-Lite-8B Accuracy: 46.5. Result ID: 69982c705698665ec4876653. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"parameters":"8B"}. This record does not assert independent reproduction. ### SpatialReasoner-7B Accuracy: 43.4. Result ID: 69982c705698665ec4876651. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"parameters":"7B"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Accuracy: 43.3. Result ID: 69982c705698665ec487664d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"parameters":"7B"}. This record does not assert independent reproduction. ### InternVL2.5-8B Accuracy: 42.4. Result ID: 69982c705698665ec487664c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"parameters":"8B"}. This record does not assert independent reproduction. ### LLaVA-OneVision-7B Accuracy: 36. Result ID: 69982c705698665ec487664f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"parameters":"7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.