List your company

Code Generation on LiveBench (test)

56.5Sig. ScoreQwen2.5-14B-Ins. + CoSPlay w/ Cluster
35.38840.86946.3551.831May 22, 2026

Evaluation results

MethodLinks
Qwen2.5-14B-Ins. + CoSPlay w/ ClusterBackbone=Ins., #GT Data=02026.0556.570.147.957.6
Qwen2.5-14B-Ins. + CoSPlayBackbone=Ins., #GT Data=02026.0554.970.147.955.7
CURE-14B + CoSPlay w/ ClusterBackbone=Ins., #GT Data=4.5k2026.0554.971.552.460.7
CURE-7B + CoSPlay w/ ClusterBackbone=Ins., #GT Data=4.5k2026.0553.666.245.452.3
CURE-14BBackbone=Ins., #GT Data=4.5k2026.0553.677.347.759.9
CURE-14B + CoSPlayBackbone=Ins., #GT Data=4.5k2026.0553.671.552.461.2
CURE-7BBackbone=Ins., #GT Data=4.5k2026.0552.354.637.451.6
CURE-7B + CoSPlayBackbone=Ins., #GT Data=4.5k2026.0551.366.245.452.1
Qwen2.5-7B-Ins. + CoSPlay w/ ClusterBackbone=Ins., #GT Data=02026.0550.366.738.849.7
Qwen2.5-14B-Instruct + CodeTBackbone=Ins., #GT Data=-2026.0549.526.439.252.1
Qwen2.5-14B-Instruct + ClusterBackbone=Ins., #GT Data=-2026.0548.426.439.252.1
Qwen2.5-14B-Coder-Ins.Backbone=Coder-Ins., #GT Data=-2026.0548.237.847.253.9
Qwen2.5-14B-InstructBackbone=Ins., #GT Data=-2026.0547.726.439.251
Qwen2.5-7B-Ins. + CoSPlayBackbone=Ins., #GT Data=02026.0547.466.738.850
DeepSeek-Coder-V2-16BBackbone=-, #GT Data=-2026.0545.83137.438.3
AZR-7B-CoderBackbone=Coder, #GT Data=02026.0544.523.112.534.9
Seed-Coder-8B-InstructBackbone=-, #GT Data=-2026.0543.526.937.645.1
AceCoder-7B-RuleBackbone=Coder-Ins., #GT Data=22k2026.0543.517.236.145.8
AceCoder-7B-RMBackbone=Coder-Ins., #GT Data=329k2026.054317.737.548.4
Qwen2.5-7B-Instruct + ClusterBackbone=Ins., #GT Data=-2026.0542.7933.142.7
Qwen2.5-7B-Coder-Ins.Backbone=Coder-Ins., #GT Data=-2026.0542.712.536.347.7
Qwen2.5-14B-CoderBackbone=Coder, #GT Data=-2026.0542.213.910.830.2
Qwen2.5-7B-CoderBackbone=Coder, #GT Data=-2026.0540.612.13.819
AZR-14B-CoderBackbone=Coder, #GT Data=02026.0539.822.238.943.5
Qwen2.5-7B-Instruct + CodeTBackbone=Ins., #GT Data=-2026.0537.5933.137.5
Qwen2.5-7B-InstructBackbone=Ins., #GT Data=-2026.0536.2933.136.2