Multimodal & Grounded benchmark
DynaMath leaderboard
Every model the catalog carries a published DynaMath value for, ranked by that value.
CategoryMultimodal & Grounded
MeasureMultimodal mathematical reasoning
TasksDynamic visual math problems
DifficultyAdvanced multimodal mathematics
Published byQwen3.6 launch benchmarks
A multimodal benchmark for dynamic mathematical reasoning over visual and structured inputs.
DynaMath ranking
1 model with a published DynaMath 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 | Multimodal mathematical reasoning |
|---|---|---|---|
| 1 |  Qwen3.6-27B | Alibaba | 85.6 |
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.