List your company

Code Generation on LiveCodeBench Easy 2025-02-01 – present

100Pass@1Gemini-2.5
99.68899.76999.8599.931Jan 29, 2026

Evaluation results

MethodLinks
Gemini-2.52026.01100
O3Reasoning Effort=High2026.01100
O4-miniReasoning Effort=High2026.01100
Self-CertaintyBase Model=O4-mini (High), Test-time Scaling Strategy=Self-Certainty2026.01100
ORMBase Model=O4-mini (High), Test-time Scaling Strategy=Outcome Reward Models2026.01100
Skywork-PRMBase Model=O4-mini (High), Test-time Scaling Strategy=Skywork-PRM2026.01100
FunPRMBase Model=O4-mini (High), Test-time Scaling Strategy=FunPRM2026.01100
DeepSeek-R12026.0199.7