List your company

Code Generation on CodeContests (Signal, UT, Code, BoN)

38SignalBaseline
26.87229.76132.6535.539May 22, 2026

Evaluation results

MethodLinks
BaselineModel=DeepSeek-V3.2-685B, Model Category=Base Models2026.053876.358.863.3
+ ClusterModel=DeepSeek-V3.2-685B, Model Category=Base Models2026.053676.960.266.7
CoSPlay (Ours)Model=DeepSeek-V3.2-685B, Model Category=Base Models2026.0535.376.960.266
CoSPlay (Ours)Model=Seed-Coder-8B-Instruct, Model Category=Base Models2026.053477.429.535.3
+ ClusterModel=Seed-Coder-8B-Instruct, Model Category=Base Models2026.053477.429.535.3
BaselineModel=DeepSeek-Coder-V2-Lite-Instruct-16B, Model Category=Base Models2026.053451.922.834
+ ClusterModel=AceCoder-Rule-7B, Model Category=RL-tuned Models2026.053472.725.533.3
CoSPlay (Ours)Model=AceCoder-Rule-7B, Model Category=RL-tuned Models2026.0533.372.725.534
CoSPlay (Ours)Model=Gemini-2.0-Flash, Model Category=Base Models2026.0532.76748.750.7
+ ClusterModel=Gemini-2.0-Flash, Model Category=Base Models2026.0532.76748.751.3
+ ClusterModel=AceCoder-RM-7B, Model Category=RL-tuned Models2026.0532.673.525.834.7
CoSPlay (Ours)Model=DeepSeek-Coder-V2-Lite-Instruct-16B, Model Category=Base Models2026.053282.835.840.7
+ ClusterModel=DeepSeek-Coder-V2-Lite-Instruct-16B, Model Category=Base Models2026.0531.382.835.841.3
CoSPlay (Ours)Model=AceCoder-RM-7B, Model Category=RL-tuned Models2026.0531.373.525.834.7
BaselineModel=Gemini-2.0-Flash, Model Category=Base Models2026.0530.736.244.948.7
CoSPlay (Ours)Model=Absolute-Zero-7B, Model Category=RL-tuned Models2026.0530.788.921.723.3
+ ClusterModel=Absolute-Zero-7B, Model Category=RL-tuned Models2026.0529.388.921.726.7
BaselineModel=Seed-Coder-8B-Instruct, Model Category=Base Models2026.0528.721.416.626.7
BaselineModel=Absolute-Zero-7B, Model Category=RL-tuned Models2026.052828.58.923.3
BaselineModel=AceCoder-Rule-7B, Model Category=RL-tuned Models2026.0527.35.323.325.3
BaselineModel=AceCoder-RM-7B, Model Category=RL-tuned Models2026.0527.38.522.425.3