List your company

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

58.7SignalBaseline
42.0646.3850.755.02May 22, 2026

Evaluation results

MethodLinks
BaselineModel=DeepSeek-V3.2-685B, Model Category=Base Models2026.0558.782.168.577.3
CoSPlay (Ours)Model=DeepSeek-V3.2-685B, Model Category=Base Models2026.0557.37476.976.7
+ ClusterModel=DeepSeek-V3.2-685B, Model Category=Base Models2026.0557.37476.976
BaselineModel=Gemini-2.0-Flash, Model Category=Base Models2026.0556.750.359.868
+ ClusterModel=AceCoder-RM-7B, Model Category=RL-tuned Models2026.0556.761.34756
CoSPlay (Ours)Model=AceCoder-RM-7B, Model Category=RL-tuned Models2026.055461.34756.7
+ ClusterModel=DeepSeek-Coder-V2-Lite-Instruct-16B, Model Category=Base Models2026.0553.368.74251.3
+ ClusterModel=Gemini-2.0-Flash, Model Category=Base Models2026.0553.376.263.266
CoSPlay (Ours)Model=DeepSeek-Coder-V2-Lite-Instruct-16B, Model Category=Base Models2026.0552.768.74248
+ ClusterModel=AceCoder-Rule-7B, Model Category=RL-tuned Models2026.0552.764.645.254.7
+ ClusterModel=Seed-Coder-8B-Instruct, Model Category=Base Models2026.055263.347.556
+ ClusterModel=Absolute-Zero-7B, Model Category=RL-tuned Models2026.055280.43347.3
CoSPlay (Ours)Model=Gemini-2.0-Flash, Model Category=Base Models2026.0551.376.263.264.7
CoSPlay (Ours)Model=AceCoder-Rule-7B, Model Category=RL-tuned Models2026.0551.364.645.254.7
CoSPlay (Ours)Model=Seed-Coder-8B-Instruct, Model Category=Base Models2026.0550.763.347.556
BaselineModel=DeepSeek-Coder-V2-Lite-Instruct-16B, Model Category=Base Models2026.0548.727.430.838.7
BaselineModel=Seed-Coder-8B-Instruct, Model Category=Base Models2026.054826.840.750.7
BaselineModel=Absolute-Zero-7B, Model Category=RL-tuned Models2026.054419.311.636.7
BaselineModel=AceCoder-Rule-7B, Model Category=RL-tuned Models2026.054413.940.746
BaselineModel=AceCoder-RM-7B, Model Category=RL-tuned Models2026.0543.315.140.948.7
CoSPlay (Ours)Model=Absolute-Zero-7B, Model Category=RL-tuned Models2026.0542.780.43340.7