# Real-world cross-view spatial reasoning on STARE Source: [Real-world cross-view spatial reasoning on STARE]() Collection index: [llms.txt]() Data updated: 2026-05-27T10:21:13.065Z Evaluation of model performance on the STARE dataset, focusing on Real-world cross-view spatial reasoning capabilities, 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 | Real-world cross-view spatial reasoning | | Dataset (including any stated split) | STARE | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 | | --- | --- | --- | --- | | Panoramic + VDrop | 35.6 | Not recorded | 6a167ad9dbd7150506f802fe | | Point Matching + VDrop | 34.4 | Not recorded | 6a167ad9dbd7150506f802fe | | Panoramic | 32.4 | Not recorded | 6a167ad9dbd7150506f802fe | | Qwen3-VL-8B | 31.6 | Not recorded | 6a167ad9dbd7150506f802fe | | Qwen3-VL-4B | 29.2 | Not recorded | 6a167ad9dbd7150506f802fe | | ThinkMorph (24K) | 28.8 | Not recorded | 6a167ad9dbd7150506f802fe | | BAGEL-Zebra-CoT (182K) | 28.4 | Not recorded | 6a167ad9dbd7150506f802fe | | BAGEL | 28 | Not recorded | 6a167ad9dbd7150506f802fe | | Top-down | 28 | Not recorded | 6a167ad9dbd7150506f802fe | | Text CoT | 26 | Not recorded | 6a167ad9dbd7150506f802fe | | Top-down + VDrop | 26 | Not recorded | 6a167ad9dbd7150506f802fe | | No-Think | 24.8 | Not recorded | 6a167ad9dbd7150506f802fe | | Point Matching | 24 | Not recorded | 6a167ad9dbd7150506f802fe | ### Panoramic + VDrop Accuracy: 35.6. Result ID: 6a16c560fbc373592c108b74. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"VDrop":"✓"}. This record does not assert independent reproduction. ### Point Matching + VDrop Accuracy: 34.4. Result ID: 6a16c560fbc373592c108b76. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"VDrop":"✓"}. This record does not assert independent reproduction. ### Panoramic Accuracy: 32.4. Result ID: 6a16c560fbc373592c108b73. [Reporting paper]() Recorded evaluation configuration: {"VDrop":"✗"}. This record does not assert independent reproduction. ### Qwen3-VL-8B Accuracy: 31.6. Result ID: 6a16c560fbc373592c108b6d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"VDrop":"✗"}. This record does not assert independent reproduction. ### Qwen3-VL-4B Accuracy: 29.2. Result ID: 6a16c560fbc373592c108b6c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"VDrop":"✗"}. This record does not assert independent reproduction. ### ThinkMorph (24K) Accuracy: 28.8. Result ID: 6a16c560fbc373592c108b70. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"VDrop":"✗"}. This record does not assert independent reproduction. ### BAGEL-Zebra-CoT (182K) Accuracy: 28.4. Result ID: 6a16c560fbc373592c108b6f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"VDrop":"✗"}. This record does not assert independent reproduction. ### BAGEL Accuracy: 28. Result ID: 6a16c560fbc373592c108b6e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"VDrop":"✗"}. This record does not assert independent reproduction. ### Top-down Accuracy: 28. Result ID: 6a16c560fbc373592c108b77. [Reporting paper]() Recorded evaluation configuration: {"VDrop":"✗"}. This record does not assert independent reproduction. ### Text CoT Accuracy: 26. Result ID: 6a16c560fbc373592c108b72. [Reporting paper]() Recorded evaluation configuration: {"VDrop":"✗"}. This record does not assert independent reproduction. ### Top-down + VDrop Accuracy: 26. Result ID: 6a16c560fbc373592c108b78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"VDrop":"✓"}. This record does not assert independent reproduction. ### No-Think Accuracy: 24.8. Result ID: 6a16c560fbc373592c108b71. [Reporting paper]() Recorded evaluation configuration: {"VDrop":"✗"}. This record does not assert independent reproduction. ### Point Matching Accuracy: 24. Result ID: 6a16c560fbc373592c108b75. [Reporting paper]() Recorded evaluation configuration: {"VDrop":"✗"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.