# Fine-Grained Perception on HR-Bench 4K Source: [Fine-Grained Perception on HR-Bench 4K]() Collection index: [llms.txt]() Data updated: 2026-06-16T10:22:48.034Z Evaluation of model performance on the HR-Bench 4K dataset focusing on Fine-Grained Perception capabilities, measured by the Score metric. 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 | Fine-Grained Perception | | Dataset (including any stated split) | HR-Bench 4K | | Metric | Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | 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 - [Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Score | Result date | Report paper | | --- | --- | --- | --- | | Gemini-3-Flash | 87.9 | Not recorded | 6a30d8e3d33dfb23e783d014 | | Qwen3-VL + LOCUS | 77 | Not recorded | 6a30d8e3d33dfb23e783d014 | | Qwen3-VL | 75.4 | Not recorded | 6a30d8e3d33dfb23e783d014 | | MiMo-VL + LOCUS | 72 | Not recorded | 6a30d8e3d33dfb23e783d014 | | Qwen2.5-VL + LOCUS | 71.6 | Not recorded | 6a30d8e3d33dfb23e783d014 | | Qwen2.5-VL | 69.9 | Not recorded | 6a30d8e3d33dfb23e783d014 | | MiMo-VL | 69.5 | Not recorded | 6a30d8e3d33dfb23e783d014 | | GPT-5.1 | 67 | Not recorded | 6a30d8e3d33dfb23e783d014 | ### Gemini-3-Flash Score: 87.9. Result ID: 6a3123e4fbc373592c2e2f66. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-VL + LOCUS Score: 77. Result ID: 6a3123e4fbc373592c2e2f6a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"4B"}. This record does not assert independent reproduction. ### Qwen3-VL Score: 75.4. Result ID: 6a3123e4fbc373592c2e2f69. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"4B"}. This record does not assert independent reproduction. ### MiMo-VL + LOCUS Score: 72. Result ID: 6a3123e4fbc373592c2e2f6c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### Qwen2.5-VL + LOCUS Score: 71.6. Result ID: 6a3123e4fbc373592c2e2f68. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### Qwen2.5-VL Score: 69.9. Result ID: 6a3123e4fbc373592c2e2f67. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### MiMo-VL Score: 69.5. Result ID: 6a3123e4fbc373592c2e2f6b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction. ### GPT-5.1 Score: 67. Result ID: 6a3123e4fbc373592c2e2f65. [Reporting 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.