Code Generation on LiveCodeBench Easy 2025-02-01 – present
100Pass@1Gemini-2.5
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-2.52026.01 | 100 | |
| O3Reasoning Effort=High2026.01 | 100 | |
| O4-miniReasoning Effort=High2026.01 | 100 | |
| Self-CertaintyBase Model=O4-mini (High), Test-time Scaling Strategy=Self-Certainty2026.01 | 100 | |
| ORMBase Model=O4-mini (High), Test-time Scaling Strategy=Outcome Reward Models2026.01 | 100 | |
| Skywork-PRMBase Model=O4-mini (High), Test-time Scaling Strategy=Skywork-PRM2026.01 | 100 | |
| FunPRMBase Model=O4-mini (High), Test-time Scaling Strategy=FunPRM2026.01 | 100 | |
| DeepSeek-R12026.01 | 99.7 |