Competitive Coding on CodeForces
49.9Best@8Agentic Verifier
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Agentic VerifierPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 49.9 | 50.9 | |
| Random GeneratorPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 46.7 | 45.4 | |
| CodeRMPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 45.9 | 45.1 | |
| CodeTPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 44.6 | 46.9 | |
| MBR-Exec (soft)Policy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 43.8 | 45.4 | |
| Agentic VerifierPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 43 | 46.4 | |
| MBR-Exec (hard)Policy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 40 | 42.2 | |
| VanillaPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 39.7 | 39.7 | |
| Grading RMPolicy Model=Qwen3-235B-A22B-Thinking-25072026.02 | 39.7 | 34.4 | |
| Random GeneratorPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 39.5 | 40.1 | |
| CodeRMPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 38.9 | 42.3 | |
| CodeTPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 38.6 | 40.1 | |
| MBR-Exec (soft)Policy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 38.3 | 41.8 | |
| MBR-Exec (hard)Policy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 33.4 | 33.7 | |
| VanillaPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 33.2 | 33.2 | |
| Grading RMPolicy Model=Qwen3-30B-A3B-Thinking-25072026.02 | 33 | 32.8 |