# 4D Understanding on R4D-Bench (All) Source: [4D Understanding on R4D-Bench (All)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:35:52.043Z Evaluation of model performance on the R4D-Bench (All) dataset for 4D Understanding tasks. 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 | 4D Understanding | | Dataset (including any stated split) | R4D-Bench (All) | | Metric | Average Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 9 of 9 | | 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 - [Average Score](): Higher is better; unit: PERCENT. - [Static Performance](): Higher is better; unit: PERCENT. - [Dynamic Performance](): Higher is better; unit: PERCENT. - [Visual Grounding Score](): Higher is better; unit: PERCENT. - [Detection Metric](): Higher is better; unit: PERCENT. - [Scene Representation Score](): Higher is better; unit: PERCENT. - [Recall](): Higher is better; unit: PERCENT. - [Completion Score](): Higher is better; unit: PERCENT. - [Tracking Accuracy](): Higher is better; unit: PERCENT. - [Frame Prediction Score](): Higher is better; unit: PERCENT. - [Semantic Accuracy](): Higher is better; unit: PERCENT. - [Depth Precision](): Higher is better; unit: PERCENT. ## Recorded results | Method | Average Score | Result date | Report paper | | --- | --- | --- | --- | | GPT-4o | 42.8 | Not recorded | 6948d086423ea42265729f78 | | 4D-RGPT | 42.2 | Not recorded | 6948d086423ea42265729f78 | | Qwen2.5-VL | 40.6 | Not recorded | 6948d086423ea42265729f78 | | LLaVA-Video | 39.7 | Not recorded | 6948d086423ea42265729f78 | | ViLaSR | 39.6 | Not recorded | 6948d086423ea42265729f78 | | SpatialReasoner | 38.3 | Not recorded | 6948d086423ea42265729f78 | | NVILA-Lite | 37.9 | Not recorded | 6948d086423ea42265729f78 | | SpaceR | 37 | Not recorded | 6948d086423ea42265729f78 | | Random | 23.4 | Not recorded | 6948d086423ea42265729f78 | ### GPT-4o Average Score: 42.8. Result ID: 69982c705698665ec487661e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### 4D-RGPT Average Score: 42.2. Result ID: 69982c705698665ec4876625. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"8B"}. This record does not assert independent reproduction. ### Qwen2.5-VL Average Score: 40.6. Result ID: 69982c705698665ec487661f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### LLaVA-Video Average Score: 39.7. Result ID: 69982c705698665ec4876620. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### ViLaSR Average Score: 39.6. Result ID: 69982c705698665ec4876621. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### SpatialReasoner Average Score: 38.3. Result ID: 69982c705698665ec4876622. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### NVILA-Lite Average Score: 37.9. Result ID: 69982c705698665ec4876624. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"8B"}. This record does not assert independent reproduction. ### SpaceR Average Score: 37. Result ID: 69982c705698665ec4876623. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction. ### Random Average Score: 23.4. Result ID: 69982c705698665ec487661d. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.