List your company

Code Generation on Hard Corpus 4 (192 problems)

75.5S-optAlgoSkill
40.34849.47458.667.726Jun 29, 2026

Evaluation results

MethodLinks
AlgoSkillBackbone=GPT-5.5, Judge Model=Haiku judge2026.0675.55.7
DirectBackbone=GPT-5.5, Judge Model=Haiku judge2026.0669.8—
AlgoSkillBackbone=gpt-oss-120b, Judge Model=Haiku judge2026.0657.315.6
DirectBackbone=gpt-oss-120b, Judge Model=Haiku judge2026.0641.7—