# STEM & Puzzle on VisuLogic (test) Source: [STEM & Puzzle on VisuLogic (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:31:29.286Z Evaluation of model performance on the test split of the VisuLogic dataset for STEM & Puzzle tasks, measured by Accuracy. 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 | STEM & Puzzle | | Dataset (including any stated split) | VisuLogic (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Qwen3-VL 32B | 32.4 | Not recorded | 697c3b66a8b01e76cc8da6e1 | | Gemini-2.5 Flash | 31 | Not recorded | 697c3b66a8b01e76cc8da6e1 | | MMFineReason-8B | 30.5 | Not recorded | 697c3b66a8b01e76cc8da6e1 | | MMFineReason-4B | 29.8 | Not recorded | 697c3b66a8b01e76cc8da6e1 | | MMFineReason-2B | 28.3 | Not recorded | 697c3b66a8b01e76cc8da6e1 | | Qwen3-VL 8B | 27.5 | Not recorded | 697c3b66a8b01e76cc8da6e1 | | GPT5 mini | 27.2 | Not recorded | 697c3b66a8b01e76cc8da6e1 | | Qwen3-VL 30B-A3B | 26.6 | Not recorded | 697c3b66a8b01e76cc8da6e1 | | HoneyBee 8B | 25.9 | Not recorded | 697c3b66a8b01e76cc8da6e1 | | MMR1 8B | 25.4 | Not recorded | 697c3b66a8b01e76cc8da6e1 | | OMR 7B | 24.4 | Not recorded | 697c3b66a8b01e76cc8da6e1 | ### Qwen3-VL 32B Accuracy: 32.4. Result ID: 6997797c5698665ec4cdd091. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Source Category":"Open-weight VLMs","Model Parameters":"32B","Evaluation Mode":"Thinking Mode"}. This record does not assert independent reproduction. ### Gemini-2.5 Flash Accuracy: 31. Result ID: 6997797c5698665ec4cdd08d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Source Category":"Closed-source VLMs","Evaluation Mode":"Thinking Mode"}. This record does not assert independent reproduction. ### MMFineReason-8B Accuracy: 30.5. Result ID: 6997797c5698665ec4cdd097. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Source Category":"Ours","Model Parameters":"8B","Evaluation Mode":"Thinking Mode"}. This record does not assert independent reproduction. ### MMFineReason-4B Accuracy: 29.8. Result ID: 6997797c5698665ec4cdd096. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Source Category":"Ours","Model Parameters":"4B","Evaluation Mode":"Thinking Mode"}. This record does not assert independent reproduction. ### MMFineReason-2B Accuracy: 28.3. Result ID: 6997797c5698665ec4cdd095. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Source Category":"Ours","Model Parameters":"2B","Evaluation Mode":"Thinking Mode"}. This record does not assert independent reproduction. ### Qwen3-VL 8B Accuracy: 27.5. Result ID: 6997797c5698665ec4cdd08f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Source Category":"Open-weight VLMs","Model Parameters":"8B","Evaluation Mode":"Thinking Mode"}. This record does not assert independent reproduction. ### GPT5 mini Accuracy: 27.2. Result ID: 6997797c5698665ec4cdd08e. [Reporting paper]() Recorded evaluation configuration: {"Model Source Category":"Closed-source VLMs","Evaluation Mode":"Thinking Mode"}. This record does not assert independent reproduction. ### Qwen3-VL 30B-A3B Accuracy: 26.6. Result ID: 6997797c5698665ec4cdd090. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Source Category":"Open-weight VLMs","Model Parameters":"30B-A3B","Evaluation Mode":"Thinking Mode"}. This record does not assert independent reproduction. ### HoneyBee 8B Accuracy: 25.9. Result ID: 6997797c5698665ec4cdd093. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Source Category":"Open-source VLMs","Model Parameters":"8B","Evaluation Mode":"Thinking Mode"}. This record does not assert independent reproduction. ### MMR1 8B Accuracy: 25.4. Result ID: 6997797c5698665ec4cdd092. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Source Category":"Open-source VLMs","Model Parameters":"8B","Evaluation Mode":"Thinking Mode"}. This record does not assert independent reproduction. ### OMR 7B Accuracy: 24.4. Result ID: 6997797c5698665ec4cdd094. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Source Category":"Open-source VLMs","Model Parameters":"7B","Evaluation Mode":"Thinking Mode"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.