Code Generation on LiveCodeBench v6 (Pass@4)
62.9Pass@4CPPO
Evaluation Results
| Method | Links | |
|---|---|---|
| CPPOModel=Gemma 4 E4B, K budget=42026.05 | 62.9 | |
| PKPOModel=Gemma 4 E4B, K budget=42026.05 | 60.1 | |
| Pass@K Training / RLVRModel=Gemma 4 E4B, K budget=42026.05 | 59.8 | |
| CPPOModel=Gemma 4 E2B, K budget=42026.05 | 56.1 | |
| PlanSearchModel=Gemma 4 E4B, K budget=42026.05 | 56 | |
| Plan-and-SolveModel=Gemma 4 E4B, K budget=42026.05 | 53.1 | |
| PKPOModel=Gemma 4 E2B, K budget=42026.05 | 52.1 | |
| Direct SolveModel=Gemma 4 E4B, K budget=42026.05 | 52 | |
| Pass@K Training / RLVRModel=Gemma 4 E2B, K budget=42026.05 | 51.9 | |
| PlanSearchModel=Gemma 4 E2B, K budget=42026.05 | 48.1 | |
| Plan-and-SolveModel=Gemma 4 E2B, K budget=42026.05 | 45.2 | |
| Direct SolveModel=Gemma 4 E2B, K budget=42026.05 | 44 | |
| PMDModel=Qwen3-8B2026.07 | 0.517 | |
| PMDModel=OLMo3-Instruct-7B2026.07 | 0.511 | |
| SDPOModel=Qwen3-8B2026.07 | 0.479 | |
| SDPOModel=OLMo3-Instruct-7B2026.07 | 0.45 | |
| GRPOModel=Qwen3-8B2026.07 | 0.412 | |
| GRPOModel=OLMo3-Instruct-7B2026.07 | 0.361 | |
| Base PolicyModel=OLMo3-Instruct-7B2026.07 | 0.277 | |
| Base PolicyModel=Qwen3-8B2026.07 | 0.271 |