Competitive Coding on ICPC-Eval
29.9Best@8Agentic Verifier
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Agentic VerifierPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 29.9 | 31.2 | |
| Random GeneratorPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 28.7 | 29.7 | |
| CodeTPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 26.9 | 27.4 | |
| CodeRMPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 26.7 | 27.1 | |
| MBR-Exec (soft)Policy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 26.2 | 26.4 | |
| MBR-Exec (hard)Policy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 23.9 | 27.4 | |
| VanillaPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 23.6 | 23.6 | |
| Grading RMPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 23.5 | 22 | |
| Agentic VerifierPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 23.1 | 25.8 | |
| Random GeneratorPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 22.4 | 22.2 | |
| CodeTPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 21.6 | 21.3 | |
| CodeRMPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 21.3 | 18.5 | |
| MBR-Exec (soft)Policy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 20.5 | 20.5 | |
| Grading RMPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 18.1 | 13.6 | |
| MBR-Exec (hard)Policy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 17.7 | 19.8 | |
| VanillaPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 16.6 | 16.6 |