# Multimodal Math Question Answering on MathVista GPS Source: [Multimodal Math Question Answering on MathVista GPS]() Collection index: [llms.txt]() Data updated: 2026-06-15T07:28:31.534Z Evaluation of model performance on the MathVista GPS dataset for multimodal mathematical question answering tasks, typically 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 | Multimodal Math Question Answering | | Dataset (including any stated split) | MathVista GPS | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 | | --- | --- | --- | --- | | VeriGeo | 75.96 | Not recorded | 6a2f86e0d33dfb23e783be19 | | GeoGen-SFT-7B | 74 | Not recorded | 6a2f86e0d33dfb23e783be19 | | MathCoder-VL-8B | 73.6 | Not recorded | 6a2f86e0d33dfb23e783be19 | | TR-CoT-8B | 73.1 | Not recorded | 6a2f86e0d33dfb23e783be19 | | InternVL2-76B | 67.8 | Not recorded | 6a2f86e0d33dfb23e783be19 | | GeoGen-SFT-3B | 64.5 | Not recorded | 6a2f86e0d33dfb23e783be19 | | MathGLM-Vision-9B | 64.42 | Not recorded | 6a2f86e0d33dfb23e783be19 | | MAVIS-7B | 64.1 | Not recorded | 6a2f86e0d33dfb23e783be19 | | Math-LLaVA-13B | 57.7 | Not recorded | 6a2f86e0d33dfb23e783be19 | | G-LLaVA-13B | 56.7 | Not recorded | 6a2f86e0d33dfb23e783be19 | | G-LLaVA-7B | 53.4 | Not recorded | 6a2f86e0d33dfb23e783be19 | | Qwen2.5-VL-7B-Instruct | 53.37 | Not recorded | 6a2f86e0d33dfb23e783be19 | | Math-PUMA-Qwen2 | 48.1 | Not recorded | 6a2f86e0d33dfb23e783be19 | ### VeriGeo Accuracy: 75.96. Result ID: 6a2fa81efbc373592c2b8cfe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"7B","Data Scale":"8.7k"}. This record does not assert independent reproduction. ### GeoGen-SFT-7B Accuracy: 74. Result ID: 6a2fa81efbc373592c2b8cfd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"7B","Data Scale":"224K"}. This record does not assert independent reproduction. ### MathCoder-VL-8B Accuracy: 73.6. Result ID: 6a2fa81efbc373592c2b8cf7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Params":"8B","Data Scale":"8.6M + 3M"}. This record does not assert independent reproduction. ### TR-CoT-8B Accuracy: 73.1. Result ID: 6a2fa81efbc373592c2b8cfb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"8B","Data Scale":"87K"}. This record does not assert independent reproduction. ### InternVL2-76B Accuracy: 67.8. Result ID: 6a2fa81efbc373592c2b8cf2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Params":"76B"}. This record does not assert independent reproduction. ### GeoGen-SFT-3B Accuracy: 64.5. Result ID: 6a2fa81efbc373592c2b8cfc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"3B","Data Scale":"224K"}. This record does not assert independent reproduction. ### MathGLM-Vision-9B Accuracy: 64.42. Result ID: 6a2fa81efbc373592c2b8cf5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"9B","Data Scale":"MathVL + VQA"}. This record does not assert independent reproduction. ### MAVIS-7B Accuracy: 64.1. Result ID: 6a2fa81efbc373592c2b8cfa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"7B","Data Scale":"834K"}. This record does not assert independent reproduction. ### Math-LLaVA-13B Accuracy: 57.7. Result ID: 6a2fa81efbc373592c2b8cf4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"13B","Data Scale":"360K"}. This record does not assert independent reproduction. ### G-LLaVA-13B Accuracy: 56.7. Result ID: 6a2fa81efbc373592c2b8cf9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"13B","Data Scale":"170K"}. This record does not assert independent reproduction. ### G-LLaVA-7B Accuracy: 53.4. Result ID: 6a2fa81efbc373592c2b8cf8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"7B","Data Scale":"170K"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B-Instruct Accuracy: 53.37. Result ID: 6a2fa81efbc373592c2b8cf3. [Reporting paper]() Recorded evaluation configuration: {"Params":"7B"}. This record does not assert independent reproduction. ### Math-PUMA-Qwen2 Accuracy: 48.1. Result ID: 6a2fa81efbc373592c2b8cf6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Params":"7B/8B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.