List your company

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

46.7Signal Score+ Cluster
28.60433.3023842.698May 22, 2026

Evaluation results

MethodLinks
+ ClusterModel=DeepSeek-V3.2-685B, Model Category=Base Models2026.0546.783.278.480
CoSPlay (Ours)Model=DeepSeek-V3.2-685B, Model Category=Base Models2026.054683.278.479.3
BaselineModel=DeepSeek-V3.2-685B, Model Category=Base Models2026.0545.385.175.782.7
+ ClusterModel=AceCoder-Rule-7B, Model Category=RL-tuned Models2026.0544.769.74051.3
+ ClusterModel=AceCoder-RM-7B, Model Category=RL-tuned Models2026.054470.739.850
CoSPlay (Ours)Model=DeepSeek-Coder-V2-Lite-Instruct-16B, Model Category=Base Models2026.0543.386.643.548
+ ClusterModel=DeepSeek-Coder-V2-Lite-Instruct-16B, Model Category=Base Models2026.0543.386.643.548.7
+ ClusterModel=Gemini-2.0-Flash, Model Category=Base Models2026.0543.383.561.565.3
CoSPlay (Ours)Model=AceCoder-Rule-7B, Model Category=RL-tuned Models2026.0543.369.74051.3
CoSPlay (Ours)Model=AceCoder-RM-7B, Model Category=RL-tuned Models2026.0543.370.739.847.3
CoSPlay (Ours)Model=Seed-Coder-8B-Instruct, Model Category=Base Models2026.0542.775.942.252.7
+ ClusterModel=Seed-Coder-8B-Instruct, Model Category=Base Models2026.0542.775.942.252.7
CoSPlay (Ours)Model=Gemini-2.0-Flash, Model Category=Base Models2026.0542.783.561.563.3
BaselineModel=Gemini-2.0-Flash, Model Category=Base Models2026.054250.256.662
BaselineModel=DeepSeek-Coder-V2-Lite-Instruct-16B, Model Category=Base Models2026.053839.928.434.7
+ ClusterModel=Absolute-Zero-7B, Model Category=RL-tuned Models2026.053684.928.136.7
CoSPlay (Ours)Model=Absolute-Zero-7B, Model Category=RL-tuned Models2026.0534.784.928.133.3
BaselineModel=Absolute-Zero-7B, Model Category=RL-tuned Models2026.0532.73111.624.7
BaselineModel=Seed-Coder-8B-Instruct, Model Category=Base Models2026.053226.532.438.7
BaselineModel=AceCoder-Rule-7B, Model Category=RL-tuned Models2026.0529.315.93436
BaselineModel=AceCoder-RM-7B, Model Category=RL-tuned Models2026.0529.317.23438