List your company

Competitive Coding on USACO

83Best@8Agentic Verifier
61.99267.44672.978.354Feb 4, 2026

Evaluation results

MethodLinks
Agentic VerifierPolicy Model=Qwen3-235B-A22B-Thinking-25072026.028384.1
Random GeneratorPolicy Model=Qwen3-235B-A22B-Thinking-25072026.0281.882.2
MBR-Exec (soft)Policy Model=Qwen3-235B-A22B-Thinking-25072026.0279.980.3
CodeTPolicy Model=Qwen3-235B-A22B-Thinking-25072026.027980.4
CodeRMPolicy Model=Qwen3-235B-A22B-Thinking-25072026.0278.777.5
Grading RMPolicy Model=Qwen3-235B-A22B-Thinking-25072026.0275.873.6
MBR-Exec (hard)Policy Model=Qwen3-235B-A22B-Thinking-25072026.0275.879.2
VanillaPolicy Model=Qwen3-235B-A22B-Thinking-25072026.0275.475.4
Agentic VerifierPolicy Model=Qwen3-30B-A3B-Thinking-25072026.0273.174.5
Random GeneratorPolicy Model=Qwen3-30B-A3B-Thinking-25072026.0269.770.2
CodeRMPolicy Model=Qwen3-30B-A3B-Thinking-25072026.0268.768.4
CodeTPolicy Model=Qwen3-30B-A3B-Thinking-25072026.0268.569.8
MBR-Exec (soft)Policy Model=Qwen3-30B-A3B-Thinking-25072026.0267.969.6
MBR-Exec (hard)Policy Model=Qwen3-30B-A3B-Thinking-25072026.0264.468.5
Grading RMPolicy Model=Qwen3-30B-A3B-Thinking-25072026.026361.9
VanillaPolicy Model=Qwen3-30B-A3B-Thinking-25072026.0262.862.8