# We-Math

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

Canonical page: https://benchlm.ai/benchmarks/wemath

- Category: [Multimodal & Grounded](/multimodal-grounded)
- Last updated: September 27, 2026

## About We-Math

- Year: 2026
- Tasks: Visually grounded math problems
- Format: Multimodal mathematical reasoning
- Difficulty: Advanced multimodal mathematics
- Paper: [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6)

We-Math is useful as a visual-math stress test because it combines symbolic reasoning with figure understanding. It helps reveal whether a model's math strength transfers into multimodal settings.

We-Math is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (0 models)

Benchmark data for this page is coming soon.

## FAQ

### What does We-Math measure?

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

### Which model scores highest on We-Math?

No models have been evaluated on We-Math yet.

### How many models are evaluated on We-Math?

0 AI models have been evaluated on We-Math on BenchLM.

### Does We-Math affect BenchLM's overall score?

Not directly. We-Math is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.