List your company

Mathematical Reasoning on OlympiadBench (pass@8)

83.82Pass@8 AccuracyOPHSD
74.647277.028679.4181.7914May 9, 2026

Evaluation results

MethodLinks
OPHSDharness=none2026.0583.82
OPSD2026.0580.88
OPHSDharness=plan-solve2026.0579.85
GRPO2026.0577.94
CRISP2026.0575