Skip to main content
ModelScale

Multimodal & Grounded benchmark

We-Math leaderboard

Every model the catalog carries a published We-Math value for, ranked by that value.

CategoryMultimodal & Grounded
MeasureMultimodal mathematical reasoning
TasksVisually grounded math problems
DifficultyAdvanced multimodal mathematics

A multimodal math benchmark for visually grounded mathematical reasoning and answer generation.

No model in the catalog has a published We-Math score.

The benchmark is defined by Qwen3.6 launch benchmarks, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.

All leaderboards