List your company

Mathematical Reasoning on AIME24 (pass@8)

83.33Pass@8GRPO
55.603662.80187077.1982May 9, 2026

Evaluation results

MethodLinks
GRPO2026.0583.33
OPSD2026.0580
OPHSDharness=plan-solve2026.0580
OPHSDharness=none2026.0579.17
CRISP2026.0556.67