Multimodal & Grounded benchmark
MathVision w/ Python leaderboard
MathVision with Python. Every model the catalog carries a published MathVision w/ Python value for, ranked by that value.
CategoryMultimodal & Grounded
MeasureImage and mathematics reasoning with tools
TasksVisual mathematics problems with Python
DifficultyAdvanced multimodal mathematics
Published byKimi K3: Open Frontier Intelligence
A tool-augmented MathVision variant that permits Python during visual mathematics reasoning.
MathVision w/ Python ranking
5 models with a published MathVision w/ Python value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Image and mathematics reasoning with tools |
|---|---|---|---|
| 1 |  Kimi K3 | Moonshot AI | 97.8 |
| 2 |  Qwen3.8 Max | Alibaba | 97.7 |
| 3 | Qwen3.8-Omni-Flash | Alibaba | 96.2 |
| 4 | Qwen3.8-Flash-Next | Alibaba | 95.7 |
| 5 | Qwen3.8-27B | Alibaba | 94.6 |
Evidence key: Observed
Rows are ordered by the value Kimi K3: Open Frontier Intelligence published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.