List your company

ResearchFormerly WizWand

Problem Generation

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

Qwen2.5-Math-72B-Inst

86.3Follow-up

16

Mar 4, 2026

Qwen2.5-Math-72B-Inst

86.3Follow-up Score

12

Mar 4, 2026