# Counting on UHR-Micro (test) Source: [Counting on UHR-Micro (test)]() Collection index: [llms.txt]() Data updated: 2026-05-13T10:54:38.155Z Evaluation of model performance on the test split of the UHR-Micro dataset for the Counting task, measured using GC, RC, CC, CRC, and Avg. 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 | Counting | | Dataset (including any stated split) | UHR-Micro (test) | | Metric | GC | | 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 - [GC](): Higher is better; unit: PERCENT. - [RC](): Higher is better; unit: PERCENT. - [CC](): Higher is better; unit: PERCENT. - [CRC](): Higher is better; unit: PERCENT. - [Avg Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | GC | Result date | Report paper | | --- | --- | --- | --- | | MAP-Agent | 40.98 | Not recorded | 6a0405dedbc836b87d8278bd | | MAP-Agent | 38.42 | Not recorded | 6a0405dedbc836b87d8278bd | | DeepEyes | 37.88 | Not recorded | 6a0405dedbc836b87d8278bd | | Qwen3-VL-235B | 33.78 | Not recorded | 6a0405dedbc836b87d8278bd | | GPT-5.2 | 33.67 | Not recorded | 6a0405dedbc836b87d8278bd | | Qwen2.5-VL-7B | 30.59 | Not recorded | 6a0405dedbc836b87d8278bd | | Qwen3-VL-30B | 29.39 | Not recorded | 6a0405dedbc836b87d8278bd | | Gemini-2.5-Pro | 28.83 | Not recorded | 6a0405dedbc836b87d8278bd | | Qwen3-VL-8B | 25.94 | Not recorded | 6a0405dedbc836b87d8278bd | | Qwen2-VL-7B | 23.83 | Not recorded | 6a0405dedbc836b87d8278bd | | GeoChat | 22.88 | Not recorded | 6a0405dedbc836b87d8278bd | | Claude 3.7 Sonnet | 19.88 | Not recorded | 6a0405dedbc836b87d8278bd | | InternVL3.5-8B | 19.4 | Not recorded | 6a0405dedbc836b87d8278bd | | InternVL3.5-38B | 3.46 | Not recorded | 6a0405dedbc836b87d8278bd | | GeoEyes | 3.13 | Not recorded | 6a0405dedbc836b87d8278bd | | GeoLLaVa-8k | 0 | Not recorded | 6a0405dedbc836b87d8278bd | ### MAP-Agent GC: 40.98. Result ID: 6a0456e047f34ce924eafabc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"Qwen3-VL-8B"}. This record does not assert independent reproduction. ### MAP-Agent GC: 38.42. Result ID: 6a0456e047f34ce924eafabb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"InternVL3.5-8B"}. This record does not assert independent reproduction. ### DeepEyes GC: 37.88. Result ID: 6a0456e047f34ce924eafab7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-VL-235B GC: 33.78. Result ID: 6a0456e047f34ce924eafab1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-5.2 GC: 33.67. Result ID: 6a0456e047f34ce924eafab4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2.5-VL-7B GC: 30.59. Result ID: 6a0456e047f34ce924eafaae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-VL-30B GC: 29.39. Result ID: 6a0456e047f34ce924eafab0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Gemini-2.5-Pro GC: 28.83. Result ID: 6a0456e047f34ce924eafab5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-VL-8B GC: 25.94. Result ID: 6a0456e047f34ce924eafaaf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2-VL-7B GC: 23.83. Result ID: 6a0456e047f34ce924eafaad. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GeoChat GC: 22.88. Result ID: 6a0456e047f34ce924eafab8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Claude 3.7 Sonnet GC: 19.88. Result ID: 6a0456e047f34ce924eafab6. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InternVL3.5-8B GC: 19.4. Result ID: 6a0456e047f34ce924eafab2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InternVL3.5-38B GC: 3.46. Result ID: 6a0456e047f34ce924eafab3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GeoEyes GC: 3.13. Result ID: 6a0456e047f34ce924eafaba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GeoLLaVa-8k GC: 0. Result ID: 6a0456e047f34ce924eafab9. [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.