# Grounding on UHR-Micro (test) Source: [Grounding on UHR-Micro (test)]() Collection index: [llms.txt]() Data updated: 2026-05-13T10:48:27.121Z Evaluation of Grounding performance on the test split of the UHR-Micro dataset, measured using metrics including GD, RD, BG, CG, MCR, and Average score. 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 | Grounding | | Dataset (including any stated split) | UHR-Micro (test) | | Metric | GD Score | | Unit | SCALAR | | 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 - [GD Score](): Higher is better; unit: SCALAR. - [RD Score](): Higher is better; unit: SCALAR. - [BG Score](): Higher is better; unit: SCALAR. - [CG Score](): Higher is better; unit: SCALAR. - [MCR (Misclassification Rate)](): Lower is better; unit: SCALAR. - [Average Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | GD Score | Result date | Report paper | | --- | --- | --- | --- | | MAP-Agent | 29.79 | Not recorded | 6a0405dedbc836b87d8278bd | | Qwen3-VL-235B | 12.39 | Not recorded | 6a0405dedbc836b87d8278bd | | Qwen3-VL-30B | 12.07 | Not recorded | 6a0405dedbc836b87d8278bd | | Gemini-2.5-Pro | 8.24 | Not recorded | 6a0405dedbc836b87d8278bd | | Qwen3-VL-8B | 6.76 | Not recorded | 6a0405dedbc836b87d8278bd | | MAP-Agent | 6.41 | Not recorded | 6a0405dedbc836b87d8278bd | | Claude 3.7 Sonnet | 5.11 | Not recorded | 6a0405dedbc836b87d8278bd | | DeepEyes | 4.23 | Not recorded | 6a0405dedbc836b87d8278bd | | GPT-5.2 | 2.33 | Not recorded | 6a0405dedbc836b87d8278bd | | InternVL3.5-8B | 1.87 | Not recorded | 6a0405dedbc836b87d8278bd | | InternVL3.5-38B | 1.7 | Not recorded | 6a0405dedbc836b87d8278bd | | GeoChat | 1.59 | Not recorded | 6a0405dedbc836b87d8278bd | | Qwen2.5-VL-7B | 1.06 | Not recorded | 6a0405dedbc836b87d8278bd | | GeoLLaVa-8k | 0.52 | Not recorded | 6a0405dedbc836b87d8278bd | | Qwen2-VL-7B | 0.18 | Not recorded | 6a0405dedbc836b87d8278bd | | GeoEyes | 0.11 | Not recorded | 6a0405dedbc836b87d8278bd | ### MAP-Agent GD Score: 29.79. Result ID: 6a0456e047f34ce924eafa9c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"Qwen3-VL-8B"}. This record does not assert independent reproduction. ### Qwen3-VL-235B GD Score: 12.39. Result ID: 6a0456e047f34ce924eafa91. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-VL-30B GD Score: 12.07. Result ID: 6a0456e047f34ce924eafa90. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Gemini-2.5-Pro GD Score: 8.24. Result ID: 6a0456e047f34ce924eafa95. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-VL-8B GD Score: 6.76. Result ID: 6a0456e047f34ce924eafa8f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MAP-Agent GD Score: 6.41. Result ID: 6a0456e047f34ce924eafa9b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"InternVL3.5-8B"}. This record does not assert independent reproduction. ### Claude 3.7 Sonnet GD Score: 5.11. Result ID: 6a0456e047f34ce924eafa96. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DeepEyes GD Score: 4.23. Result ID: 6a0456e047f34ce924eafa97. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-5.2 GD Score: 2.33. Result ID: 6a0456e047f34ce924eafa94. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InternVL3.5-8B GD Score: 1.87. Result ID: 6a0456e047f34ce924eafa92. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InternVL3.5-38B GD Score: 1.7. Result ID: 6a0456e047f34ce924eafa93. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GeoChat GD Score: 1.59. Result ID: 6a0456e047f34ce924eafa98. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2.5-VL-7B GD Score: 1.06. Result ID: 6a0456e047f34ce924eafa8e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GeoLLaVa-8k GD Score: 0.52. Result ID: 6a0456e047f34ce924eafa99. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2-VL-7B GD Score: 0.18. Result ID: 6a0456e047f34ce924eafa8d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GeoEyes GD Score: 0.11. Result ID: 6a0456e047f34ce924eafa9a. [Reporting paper]() [Method origin 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.