# MATH

> A competition-style mathematical reasoning benchmark reported in DeepSeek-V4 base-model evaluations.

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

- Category: [Mathematics](/math)
- Last updated: September 15, 2026

## About MATH

- Year: 2026
- Tasks: Competition math problems
- Format: Exact match
- Difficulty: Advanced math reasoning
- Paper: [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf)

BenchLM stores MATH as a display-only provider-table row when exact values are published in DeepSeek-V4 evaluations.

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 MATH measure?

A competition-style mathematical reasoning benchmark reported in DeepSeek-V4 base-model evaluations.

### Which model scores highest on MATH?

No models have been evaluated on MATH yet.

### How many models are evaluated on MATH?

0 AI models have been evaluated on MATH on BenchLM.

### Does MATH affect BenchLM's overall score?

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