Multimodal & Grounded benchmark
MathVision leaderboard
Every model the catalog carries a published MathVision value for, ranked by that value.
CategoryMultimodal & Grounded
MeasureImage + math reasoning
TasksVisually grounded math problems
DifficultyAdvanced multimodal mathematics
Published byQwen3.6 launch benchmarks
A visual mathematics benchmark that tests whether a model can solve math problems grounded in diagrams, equations, figures, and other visual inputs.
MathVision ranking
19 models with a published MathVision 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 + math reasoning |
|---|---|---|---|
| 1 |  Qwen3.8 Max | Alibaba | 95.2 |
| 2 |  Kimi K3 | Moonshot AI | 94.3 |
| 3 |  Seed 2.1 Pro | ByteDance | 92.6 |
| 4 | Qwen3.8-Omni-Flash | Alibaba | 91.8 |
| 5 | Qwen3.8-Flash-Next | Alibaba | 90.6 |
| 6 | Qwen3.7 Plus | Alibaba | 90.3 |
| 7 | Seed 2.1 Turbo | ByteDance | 90.1 |
| 8 | Qwen3.8-27B | Alibaba | 90.0 |
| 9 | Qwen3.5 397B | Alibaba | 88.6 |
| 10 | Qwen3.6 Plus | Alibaba | 88.0 |
| 11 | DSdots3-note Preview | Dots Studio | 87.7 |
| 12 | Kimi K2.6 | Moonshot AI | 87.4 |
| 13 |  Gemini 3 Pro | 86.6 | |
| 14 | Qwen3.5-122B-A10B | Alibaba | 86.2 |
| 15 | Qwen3.5-27B | Alibaba | 86.0 |
| 16 | Qwen3.5-35B-A3B | Alibaba | 83.9 |
| 17 |  GPT-5.2 | OpenAI | 83.0 |
| 18 | Gemma 4 12B | 79.7 | |
| 19 |  Claude Opus 4.5 | Anthropic | 74.3 |
Evidence key: Observed
Rows are ordered by the value Qwen3.6 launch benchmarks 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.