# Situated 3D Question Answering on SQA3D Source: [Situated 3D Question Answering on SQA3D]() Collection index: [llms.txt]() Data updated: 2026-03-31T09:43:50.236Z Evaluation of model performance on the SQA3D dataset for Situated 3D Question Answering, reporting Exact Match (EM) and EM-R scores. 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 | Situated 3D Question Answering | | Dataset (including any stated split) | SQA3D | | Metric | EM | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 19 of 19 | | 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 - [EM](): Higher is better; unit: PERCENT. - [EM-R](): Higher is better; unit: PERCENT. ## Recorded results | Method | EM | Result date | Report paper | | --- | --- | --- | --- | | CVP | 62.3 | Not recorded | 6938feb66cfd488761a53e5c | | 3DGraphLLM-7B + QuatRoPE | 55.2 | Not recorded | 69c60f190636e5bf4afc859b | | Chat-Scene-7B + QuatRoPE | 54.7 | Not recorded | 69c60f190636e5bf4afc859b | | Chat-Scene | 54.6 | Not recorded | 68fa74f61e209131cea64e15 | | Chat-Scene-7B | 54.6 | Not recorded | 69c60f190636e5bf4afc859b | | Scene-LLM | 54.2 | Not recorded | 68fa74f61e209131cea64e15 | | Scene-LLM | 53.6 | Not recorded | 69c60f190636e5bf4afc859b | | 3DGraphLLM-1B + QuatRoPE | 53.2 | Not recorded | 69c60f190636e5bf4afc859b | | Chat-Scene-1B + QuatRoPE | 53.1 | Not recorded | 69c60f190636e5bf4afc859b | | 3DGraphLLM-7B | 53.1 | Not recorded | 69c60f190636e5bf4afc859b | | BridgeQA | 52.9 | Not recorded | 69c60f190636e5bf4afc859b | | Chat-Scene++ | 52.9 | Not recorded | 69cb555c0636e5bf4afca218 | | 3DGraphLLM-1B | 51.1 | Not recorded | 69c60f190636e5bf4afc859b | | Chat-Scene-1B | 50.7 | Not recorded | 69c60f190636e5bf4afc859b | | 3D-VisTA | 48.5 | Not recorded | 68fa74f61e209131cea64e15 | | 3D-VisTA | 48.5 | Not recorded | 69c60f190636e5bf4afc859b | | PQ3D | 47.1 | Not recorded | 69c60f190636e5bf4afc859b | | GPT-4o | 41.7 | Not recorded | 6938feb66cfd488761a53e5c | ### CVP EM: 62.3. Result ID: 699871e65698665ec4d21230. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### 3DGraphLLM-7B + QuatRoPE EM: 55.2. Result ID: 69c676f247f34ce924b03d39. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Detector / Segmentation":"Mask3D"}. This record does not assert independent reproduction. ### Chat-Scene-7B + QuatRoPE EM: 54.7. Result ID: 69c676f247f34ce924b03d37. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Detector / Segmentation":"Mask3D"}. This record does not assert independent reproduction. ### Chat-Scene EM: 54.6. Result ID: 69936c7e3a6c31484915d652. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"LLM-based Models"}. This record does not assert independent reproduction. ### Chat-Scene-7B EM: 54.6. Result ID: 69c676f247f34ce924b03d36. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Detector / Segmentation":"Mask3D"}. This record does not assert independent reproduction. ### Scene-LLM EM: 54.2. Result ID: 69936c7e3a6c31484915d651. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"LLM-based Models"}. This record does not assert independent reproduction. ### Scene-LLM EM: 53.6. Result ID: 69c676f247f34ce924b03d31. [Reporting paper]() Recorded evaluation configuration: {"Detector / Segmentation":"N/A"}. This record does not assert independent reproduction. ### 3DGraphLLM-1B + QuatRoPE EM: 53.2. Result ID: 69c676f247f34ce924b03d35. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Detector / Segmentation":"GT"}. This record does not assert independent reproduction. ### Chat-Scene-1B + QuatRoPE EM: 53.1. Result ID: 69c676f247f34ce924b03d33. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Detector / Segmentation":"GT"}. This record does not assert independent reproduction. ### 3DGraphLLM-7B EM: 53.1. Result ID: 69c676f247f34ce924b03d38. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Detector / Segmentation":"Mask3D"}. This record does not assert independent reproduction. ### BridgeQA EM: 52.9. Result ID: 69c676f247f34ce924b03d30. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Detector / Segmentation":"VoteNet"}. This record does not assert independent reproduction. ### Chat-Scene++ EM: 52.9. Result ID: 69cb975047f34ce924b445b2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Modality":"2D-only"}. This record does not assert independent reproduction. ### 3DGraphLLM-1B EM: 51.1. Result ID: 69c676f247f34ce924b03d34. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Detector / Segmentation":"GT"}. This record does not assert independent reproduction. ### Chat-Scene-1B EM: 50.7. Result ID: 69c676f247f34ce924b03d32. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Detector / Segmentation":"GT"}. This record does not assert independent reproduction. ### 3D-VisTA EM: 48.5. Result ID: 69936c7e3a6c31484915d64f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Expert Models"}. This record does not assert independent reproduction. ### 3D-VisTA EM: 48.5. Result ID: 69c676f247f34ce924b03d2e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Detector / Segmentation":"Mask3D"}. This record does not assert independent reproduction. ### PQ3D EM: 47.1. Result ID: 69c676f247f34ce924b03d2f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Detector / Segmentation":"PQ3D Promptable"}. This record does not assert independent reproduction. ### GPT-4o EM: 41.7. Result ID: 699871e65698665ec4d2122f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"task-specific fine-tuning":"none"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.