What it measures

Multilingual mathematical reasoning benchmark across 18 languages and 4 difficulty levels.

Reading the measurement

A correct final answer, a complete proof and useful research progress are different achievements. Choose the one the task actually grades. Inspect the permitted computation, attempt budget and handling of invalid arguments before comparing models.

Published evaluation

PolyMath-Top; Mean accuracy across the published languages. Model configurations and missing observations follow the original publication.

Where this fits in an evaluation suite

Final-answer accuracy, proof credit, and expert-reviewed research progress are distinct signals. A proof-aware evaluation should retain partial work and audit strong claims.

Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.

A reproducible comparison

PolyMath-Top; Mean accuracy across the published languages. Model configurations and missing observations follow the original publication.

Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.

PRIMARY EVIDENCE & FURTHER READING

  1. PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts — published result table ↗

    Yiming Wang, Pei Zhang, Jialong Tang, Haoran Wei, Baosong Yang, Rui Wang et al. · 2025

    All 16 authors

    Yiming Wang, Pei Zhang, Jialong Tang, Haoran Wei, Baosong Yang, Rui Wang, Chenshu Sun, Feitong Sun, Jiran Zhang, Junxuan Wu, Qiqian Cang, Yichang Zhang, Fei Huang, Junyang Lin, Fei Huang, Jingren Zhou

Reviewed 2026-10-26. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.