Competitive Coding on LiveCodeBench
81.6Best@8Agentic Verifier
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Agentic VerifierPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 81.6 | 82.9 | |
| CodeRMPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 79.3 | 80.3 | |
| CodeTPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 78.8 | 79.2 | |
| Random GeneratorPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 78.8 | 78.9 | |
| MBR-Exec (soft)Policy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 78.5 | 78.5 | |
| MBR-Exec (hard)Policy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 77.9 | 77.7 | |
| Grading RMPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 75.9 | 74.9 | |
| VanillaPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 74.7 | 74.7 | |
| Agentic VerifierPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 73.6 | 73.7 | |
| CodeTPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 72.7 | 70.5 | |
| CodeRMPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 71.2 | 71.4 | |
| Random GeneratorPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 70.7 | 70.4 | |
| MBR-Exec (soft)Policy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 70 | 70 | |
| MBR-Exec (hard)Policy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 68.5 | 69.2 | |
| Grading RMPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 67.1 | 68 | |
| VanillaPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 66.2 | 66.2 |