Competitive Coding on USACO
83Best@8Agentic Verifier
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Agentic VerifierPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 83 | 84.1 | |
| Random GeneratorPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 81.8 | 82.2 | |
| MBR-Exec (soft)Policy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 79.9 | 80.3 | |
| CodeTPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 79 | 80.4 | |
| CodeRMPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 78.7 | 77.5 | |
| Grading RMPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 75.8 | 73.6 | |
| MBR-Exec (hard)Policy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 75.8 | 79.2 | |
| VanillaPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 75.4 | 75.4 | |
| Agentic VerifierPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 73.1 | 74.5 | |
| Random GeneratorPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 69.7 | 70.2 | |
| CodeRMPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 68.7 | 68.4 | |
| CodeTPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 68.5 | 69.8 | |
| MBR-Exec (soft)Policy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 67.9 | 69.6 | |
| MBR-Exec (hard)Policy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 64.4 | 68.5 | |
| Grading RMPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 63 | 61.9 | |
| VanillaPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 62.8 | 62.8 |