MathVerse
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Mathematical Multimodal Reasoning | MathVerse | Accuracy81.4 | 221 | |
| Visual Mathematical Reasoning | MathVerse | Accuracy73.56 | 135 | |
| Mathematical Reasoning | MathVerse | Accuracy81.45 | 109 | |
| Multimodal Reasoning | MathVerse | Accuracy56.2 | 84 | |
| Mathematical Reasoning | MathVerse mini | Accuracy82.6 | 67 | |
| Mathematical Visual Question Answering | MathVerse | Accuracy82.9 | 37 | |
| Mathematical Reasoning | MathVerse Vision Only | Accuracy67 | 34 | |
| Multimodal Mathematical Reasoning | MathVerse-V | Accuracy81.2 | 33 | |
| Multimodal Mathematical Reasoning | MathVerse (test) | Accuracy (ALL)64.9 | 33 | |
| STEM & Reasoning | MathVerse | Accuracy91.62 | 28 | |
| Mathematical problem solving | MathVerse (testmini) | Accuracy64.9 | 28 | |
| Visual Reasoning | MathVerse | Accuracy61.29 | 26 | |
| Multimodal Mathematical Reasoning | MathVerse mini (test) | T-Dominant Score70.94 | 26 | |
| Mathematical reasoning | MathVerse mini (test) | Accuracy66.9 | 26 | |
| Multimodal Reasoning | MathVerse MINI | Accuracy77.7 | 25 | |
| Multimodal Mathematical Reasoning | MathVerse mini | Accuracy65.9 | 22 | |
| Multimodal Autoformalization | MATHVERSE Solid Geometry | Compilation Success80 | 20 | |
| Step-wise Verification | MathVerse VO | Macro F162.8 | 18 | |
| Multimodal Reasoning | MathVerse (testmini) | Mean@1 Accuracy57.6 | 17 | |
| Visual Mathematical Reasoning | MathVerse testmini | Score63.8 | 16 | |
| Multimodal Mathematical Reasoning | MathVerse (testmini) | Accuracy57 | 16 | |
| Mathematical & Geometric Reasoning | MathVerse | Accuracy@875.1 | 16 | |
| Multimodal Mathematical Reasoning | MathVerse | Pass@1 Accuracy47.2 | 14 | |
| Visual Mathematical Reasoning | MathVerse mini Vision Only | Avg@3 Score48.6 | 14 | |
| Omni-modal reasoning | MathVerse mini (test) | Score59.3 | 13 |
Showing 25 of 58 rows