# Vision-Language Reasoning on UHR-Micro (test) Source: [Vision-Language Reasoning on UHR-Micro (test)]() Collection index: [llms.txt]() Data updated: 2026-05-13T10:54:38.238Z Evaluation of model performance on the test split of the UHR-Micro dataset for Vision-Language Reasoning. 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 | Vision-Language Reasoning | | Dataset (including any stated split) | UHR-Micro (test) | | Metric | Average Score | | 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 - [Average Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Average Score | Result date | Report paper | | --- | --- | --- | --- | | MAP-Agent | 44.1 | Not recorded | 6a0405dedbc836b87d8278bd | | Qwen3-VL-235B | 32.83 | Not recorded | 6a0405dedbc836b87d8278bd | | Qwen3-VL-30B | 31.51 | Not recorded | 6a0405dedbc836b87d8278bd | | MAP-Agent | 28.75 | Not recorded | 6a0405dedbc836b87d8278bd | | Qwen3-VL-8B | 27.99 | Not recorded | 6a0405dedbc836b87d8278bd | | Gemini-2.5-Pro | 27.46 | Not recorded | 6a0405dedbc836b87d8278bd | | DeepEyes | 26.01 | Not recorded | 6a0405dedbc836b87d8278bd | | Qwen2.5-VL-7B | 24.78 | Not recorded | 6a0405dedbc836b87d8278bd | | GPT-5.2 | 24.76 | Not recorded | 6a0405dedbc836b87d8278bd | | InternVL3.5-38B | 21.21 | Not recorded | 6a0405dedbc836b87d8278bd | | InternVL3.5-8B | 20.44 | Not recorded | 6a0405dedbc836b87d8278bd | | Qwen2-VL-7B | 19.35 | Not recorded | 6a0405dedbc836b87d8278bd | | GeoChat | 17.17 | Not recorded | 6a0405dedbc836b87d8278bd | | Claude 3.7 Sonnet | 15.37 | Not recorded | 6a0405dedbc836b87d8278bd | | GeoEyes | 9.53 | Not recorded | 6a0405dedbc836b87d8278bd | | GeoLLaVa-8k | 8.85 | Not recorded | 6a0405dedbc836b87d8278bd | ### MAP-Agent Average Score: 44.1. Result ID: 6a0456e047f34ce924eafadc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"Qwen3-VL-8B"}. This record does not assert independent reproduction. ### Qwen3-VL-235B Average Score: 32.83. Result ID: 6a0456e047f34ce924eafad1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-VL-30B Average Score: 31.51. Result ID: 6a0456e047f34ce924eafad0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MAP-Agent Average Score: 28.75. Result ID: 6a0456e047f34ce924eafadb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"InternVL3.5-8B"}. This record does not assert independent reproduction. ### Qwen3-VL-8B Average Score: 27.99. Result ID: 6a0456e047f34ce924eafacf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Gemini-2.5-Pro Average Score: 27.46. Result ID: 6a0456e047f34ce924eafad5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DeepEyes Average Score: 26.01. Result ID: 6a0456e047f34ce924eafad7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Average Score: 24.78. Result ID: 6a0456e047f34ce924eaface. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-5.2 Average Score: 24.76. Result ID: 6a0456e047f34ce924eafad4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InternVL3.5-38B Average Score: 21.21. Result ID: 6a0456e047f34ce924eafad3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InternVL3.5-8B Average Score: 20.44. Result ID: 6a0456e047f34ce924eafad2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2-VL-7B Average Score: 19.35. Result ID: 6a0456e047f34ce924eafacd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GeoChat Average Score: 17.17. Result ID: 6a0456e047f34ce924eafad8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Claude 3.7 Sonnet Average Score: 15.37. Result ID: 6a0456e047f34ce924eafad6. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GeoEyes Average Score: 9.53. Result ID: 6a0456e047f34ce924eafada. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GeoLLaVa-8k Average Score: 8.85. Result ID: 6a0456e047f34ce924eafad9. [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.