# Distance-Direction Spatial Grounding on NY Source: [Distance-Direction Spatial Grounding on NY]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:46:32.306Z Evaluation of Distance-Direction Spatial Grounding performance on the NY dataset, measured using Hit@5 and NDCG@5. 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 | Distance-Direction Spatial Grounding | | Dataset (including any stated split) | NY | | Metric | Hit@5 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [Hit@5](): Higher is better; unit: PERCENT. - [NDCG@5](): Higher is better; unit: PERCENT. ## Recorded results | Method | Hit@5 | Result date | Report paper | | --- | --- | --- | --- | | UGE | 44.35 | Not recorded | 698abbd9c97a0b3e3b5de23c | | UGE | 39.13 | Not recorded | 698abbd9c97a0b3e3b5de23c | | UGE | 36.52 | Not recorded | 698abbd9c97a0b3e3b5de23c | | UGE | 33.91 | Not recorded | 698abbd9c97a0b3e3b5de23c | | UGE | 33.04 | Not recorded | 698abbd9c97a0b3e3b5de23c | | UGE | 30.43 | Not recorded | 698abbd9c97a0b3e3b5de23c | | UGE | 29.57 | Not recorded | 698abbd9c97a0b3e3b5de23c | | Qwen2.5-VL-3B | 28.7 | Not recorded | 698abbd9c97a0b3e3b5de23c | | UGE | 27.83 | Not recorded | 698abbd9c97a0b3e3b5de23c | | Qwen2-VL-2B | 26.09 | Not recorded | 698abbd9c97a0b3e3b5de23c | | Qwen2.5-VL-7B | 26.09 | Not recorded | 698abbd9c97a0b3e3b5de23c | | GME-2B | 25.22 | Not recorded | 698abbd9c97a0b3e3b5de23c | | LLaVA1.6 | 22.61 | Not recorded | 698abbd9c97a0b3e3b5de23c | | Phi3-V | 22.61 | Not recorded | 698abbd9c97a0b3e3b5de23c | | VLM2Vec-2B | 20.87 | Not recorded | 698abbd9c97a0b3e3b5de23c | | Qwen2-VL-7B | 18.26 | Not recorded | 698abbd9c97a0b3e3b5de23c | ### UGE Hit@5: 44.35. Result ID: 699727c55698665ec47666c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction. ### UGE Hit@5: 39.13. Result ID: 699727c55698665ec47666c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"Phi3-V"}. This record does not assert independent reproduction. ### UGE Hit@5: 36.52. Result ID: 699727c55698665ec47666c6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"LLaVA1.6"}. This record does not assert independent reproduction. ### UGE Hit@5: 33.91. Result ID: 699727c55698665ec47666bc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"Qwen2-VL-7B"}. This record does not assert independent reproduction. ### UGE Hit@5: 33.04. Result ID: 699727c55698665ec47666ba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"Qwen2-VL-2B"}. This record does not assert independent reproduction. ### UGE Hit@5: 30.43. Result ID: 699727c55698665ec47666c2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"GME-2B"}. This record does not assert independent reproduction. ### UGE Hit@5: 29.57. Result ID: 699727c55698665ec47666be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"Qwen2.5-VL-3B"}. This record does not assert independent reproduction. ### Qwen2.5-VL-3B Hit@5: 28.7. Result ID: 699727c55698665ec47666bd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### UGE Hit@5: 27.83. Result ID: 699727c55698665ec47666c4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"VLM2Vec-2B"}. This record does not assert independent reproduction. ### Qwen2-VL-2B Hit@5: 26.09. Result ID: 699727c55698665ec47666b9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Hit@5: 26.09. Result ID: 699727c55698665ec47666bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GME-2B Hit@5: 25.22. Result ID: 699727c55698665ec47666c1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LLaVA1.6 Hit@5: 22.61. Result ID: 699727c55698665ec47666c5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Phi3-V Hit@5: 22.61. Result ID: 699727c55698665ec47666c7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### VLM2Vec-2B Hit@5: 20.87. Result ID: 699727c55698665ec47666c3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2-VL-7B Hit@5: 18.26. Result ID: 699727c55698665ec47666bb. [Reporting paper]() [Method origin paper]() [Implementation]() 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.