PolyMath

A multilingual mathematical reasoning benchmark that tests whether math performance transfers across languages rather than only in English.

  • Not in index
  • Multilingual
ModelsModels with a result.3
Top resultBest result on this test.N/A
Top-3 spreadPoints from first to third.N/A
YearYear of release.N/A

Results

3 results
#ModelResultThe score from the source.
Qwen3.7 Max86.5%
Qwen3.7 Plus84.0%