# Geometric Perception on GePBench 1.0 (Overall) Source: [Geometric Perception on GePBench 1.0 (Overall)]() Collection index: [llms.txt]() Data updated: 2026-06-16T09:10:53.955Z Evaluation of model performance on the Geometric Perception task using the overall set of the GePBench 1.0 dataset. 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 | Geometric Perception | | Dataset (including any stated split) | GePBench 1.0 (Overall) | | Metric | Average Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 34 of 34 | | 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 | | --- | --- | --- | --- | | Human | 99.3 | Not recorded | 68fa77071e209131cea709bb | | Qwen3.5 | 79.2 | Not recorded | 68fa77071e209131cea709bb | | Qwen3-VL | 78.8 | Not recorded | 68fa77071e209131cea709bb | | Gemini-2.5-pro | 78.6 | Not recorded | 68fa77071e209131cea709bb | | Qwen3.5 | 71.2 | Not recorded | 68fa77071e209131cea709bb | | GPT-5.2 | 71 | Not recorded | 68fa77071e209131cea709bb | | InternVL3 | 71 | Not recorded | 68fa77071e209131cea709bb | | Qwen3-VL | 67.8 | Not recorded | 68fa77071e209131cea709bb | | InternVL2.5 | 67.7 | Not recorded | 68fa77071e209131cea709bb | | Qwen2.5-VL | 66 | Not recorded | 68fa77071e209131cea709bb | | Qwen2-VL | 65.3 | Not recorded | 68fa77071e209131cea709bb | | InternVL3 | 64 | Not recorded | 68fa77071e209131cea709bb | | LLaVA-OneVision | 63.6 | Not recorded | 68fa77071e209131cea709bb | | GPT-4o | 63.2 | Not recorded | 68fa77071e209131cea709bb | | Qwen2.5-VL | 62.4 | Not recorded | 68fa77071e209131cea709bb | | Qwen2-VL | 58.6 | Not recorded | 68fa77071e209131cea709bb | | MiniCPM-V-2.6 | 57.9 | Not recorded | 68fa77071e209131cea709bb | | QVQ-preview | 57 | Not recorded | 68fa77071e209131cea709bb | | InternVL2.5 | 55.9 | Not recorded | 68fa77071e209131cea709bb | | LLaVA-OneVision | 55.8 | Not recorded | 68fa77071e209131cea709bb | | LLaMA-3.2-Vision | 55.4 | Not recorded | 68fa77071e209131cea709bb | | GLM-4V | 52.8 | Not recorded | 68fa77071e209131cea709bb | | Mantis-Idefics2 | 47.7 | Not recorded | 68fa77071e209131cea709bb | | mPLUG-Owl3 | 47.5 | Not recorded | 68fa77071e209131cea709bb | | Math-PUMA | 44.3 | Not recorded | 68fa77071e209131cea709bb | | LLaVA-1.5 | 39.1 | Not recorded | 68fa77071e209131cea709bb | | Math-LLaVA | 38.2 | Not recorded | 68fa77071e209131cea709bb | | LLaVA-1.5 | 37.1 | Not recorded | 68fa77071e209131cea709bb | | BLIP2 | 33.9 | Not recorded | 68fa77071e209131cea709bb | | InstructBLIP | 33.5 | Not recorded | 68fa77071e209131cea709bb | | G-LLaVA | 29.2 | Not recorded | 68fa77071e209131cea709bb | | MiniGPTv2 | 28.9 | Not recorded | 68fa77071e209131cea709bb | | G-LLaVA | 26.5 | Not recorded | 68fa77071e209131cea709bb | | Random guessing | 25 | Not recorded | 68fa77071e209131cea709bb | ### Human Average Score: 99.3. Result ID: 6a31130bfbc373592c2d9ee5. [Reporting paper]() Recorded evaluation configuration: {"Model Size (Parameters)":"-","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### Qwen3.5 Average Score: 79.2. Result ID: 6a31130bfbc373592c2d9efc. [Reporting paper]() Recorded evaluation configuration: {"Model Size (Parameters)":"397B-A17B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### Qwen3-VL Average Score: 78.8. Result ID: 6a31130bfbc373592c2d9efa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Parameters)":"235B-A22B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### Gemini-2.5-pro Average Score: 78.6. Result ID: 6a31130bfbc373592c2d9ee8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Parameters)":"-","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### Qwen3.5 Average Score: 71.2. Result ID: 6a31130bfbc373592c2d9efb. [Reporting paper]() Recorded evaluation configuration: {"Model Size (Parameters)":"9B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### GPT-5.2 Average Score: 71. Result ID: 6a31130bfbc373592c2d9ee7. [Reporting paper]() Recorded evaluation configuration: {"Model Size (Parameters)":"-","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### InternVL3 Average Score: 71. Result ID: 6a31130bfbc373592c2d9f00. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Parameters)":"78B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### Qwen3-VL Average Score: 67.8. Result ID: 6a31130bfbc373592c2d9ef9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Parameters)":"8B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### InternVL2.5 Average Score: 67.7. Result ID: 6a31130bfbc373592c2d9efe. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size (Parameters)":"78B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### Qwen2.5-VL Average Score: 66. Result ID: 6a31130bfbc373592c2d9ef8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Parameters)":"72B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### Qwen2-VL Average Score: 65.3. Result ID: 6a31130bfbc373592c2d9ef6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size (Parameters)":"72B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### InternVL3 Average Score: 64. Result ID: 6a31130bfbc373592c2d9eff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Parameters)":"8B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### LLaVA-OneVision Average Score: 63.6. Result ID: 6a31130bfbc373592c2d9ef4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size (Parameters)":"72B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### GPT-4o Average Score: 63.2. Result ID: 6a31130bfbc373592c2d9ee6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size (Parameters)":"-","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### Qwen2.5-VL Average Score: 62.4. Result ID: 6a31130bfbc373592c2d9ef7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Parameters)":"7B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### Qwen2-VL Average Score: 58.6. Result ID: 6a31130bfbc373592c2d9ef5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size (Parameters)":"7B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### MiniCPM-V-2.6 Average Score: 57.9. Result ID: 6a31130bfbc373592c2d9eef. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size (Parameters)":"8B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### QVQ-preview Average Score: 57. Result ID: 6a31130bfbc373592c2d9f05. [Reporting paper]() Recorded evaluation configuration: {"Model Size (Parameters)":"72B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### InternVL2.5 Average Score: 55.9. Result ID: 6a31130bfbc373592c2d9efd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size (Parameters)":"8B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### LLaVA-OneVision Average Score: 55.8. Result ID: 6a31130bfbc373592c2d9ef3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size (Parameters)":"7B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### LLaMA-3.2-Vision Average Score: 55.4. Result ID: 6a31130bfbc373592c2d9ef2. [Reporting paper]() Recorded evaluation configuration: {"Model Size (Parameters)":"90B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### GLM-4V Average Score: 52.8. Result ID: 6a31130bfbc373592c2d9ef0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Parameters)":"9B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### Mantis-Idefics2 Average Score: 47.7. Result ID: 6a31130bfbc373592c2d9ef1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Parameters)":"8B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### mPLUG-Owl3 Average Score: 47.5. Result ID: 6a31130bfbc373592c2d9eee. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size (Parameters)":"7B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### Math-PUMA Average Score: 44.3. Result ID: 6a31130bfbc373592c2d9f04. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Parameters)":"7B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### LLaVA-1.5 Average Score: 39.1. Result ID: 6a31130bfbc373592c2d9eed. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size (Parameters)":"13B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### Math-LLaVA Average Score: 38.2. Result ID: 6a31130bfbc373592c2d9f03. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Parameters)":"13B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### LLaVA-1.5 Average Score: 37.1. Result ID: 6a31130bfbc373592c2d9eec. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size (Parameters)":"7B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### BLIP2 Average Score: 33.9. Result ID: 6a31130bfbc373592c2d9ee9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size (Parameters)":"3B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### InstructBLIP Average Score: 33.5. Result ID: 6a31130bfbc373592c2d9eea. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size (Parameters)":"3B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### G-LLaVA Average Score: 29.2. Result ID: 6a31130bfbc373592c2d9f02. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Parameters)":"13B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### MiniGPTv2 Average Score: 28.9. Result ID: 6a31130bfbc373592c2d9eeb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Size (Parameters)":"7B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### G-LLaVA Average Score: 26.5. Result ID: 6a31130bfbc373592c2d9f01. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Size (Parameters)":"7B","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. ### Random guessing Average Score: 25. Result ID: 6a31130bfbc373592c2d9ee4. [Reporting paper]() Recorded evaluation configuration: {"Model Size (Parameters)":"-","Zero-shot manner":"true","Temperature":"0","Image Resolution":"640x640"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.