List your company

Code Generation on Average dataset-weighted (test)

34.1Sig. ScoreCURE-14B + CoSPlay w/ Cluster
21.6224.8628.131.34May 22, 2026

Evaluation results

MethodLinks
CURE-14B + CoSPlay w/ ClusterBackbone=Ins., #GT Data=4.5k2026.0534.180.13646.2
Qwen2.5-14B-Ins. + CoSPlay w/ ClusterBackbone=Ins., #GT Data=02026.053477.630.842
Qwen2.5-14B-Ins. + CoSPlayBackbone=Ins., #GT Data=02026.0533.877.630.841.2
CURE-14B + CoSPlayBackbone=Ins., #GT Data=4.5k2026.0533.880.13645.9
CURE-14BBackbone=Ins., #GT Data=4.5k2026.0533.682.430.141.8
CURE-7B + CoSPlay w/ ClusterBackbone=Ins., #GT Data=4.5k2026.0533.478.327.738.6
CURE-7B + CoSPlayBackbone=Ins., #GT Data=4.5k2026.053378.327.738.4
Qwen2.5-7B-Ins. + CoSPlay w/ ClusterBackbone=Ins., #GT Data=02026.0531.978.323.333.2
Qwen2.5-7B-Ins. + CoSPlayBackbone=Ins., #GT Data=02026.0531.378.323.332.6
CURE-7BBackbone=Ins., #GT Data=4.5k2026.053154.922.532.9
DeepSeek-Coder-V2-16BBackbone=-, #GT Data=-2026.0530.14119.529.6
Qwen2.5-14B-Instruct + CodeTBackbone=Ins., #GT Data=-2026.0529.732.423.934.3
Qwen2.5-14B-InstructBackbone=Ins., #GT Data=-2026.0529.132.423.933.2
Qwen2.5-14B-Instruct + ClusterBackbone=Ins., #GT Data=-2026.052932.423.933.8
Qwen2.5-14B-Coder-Ins.Backbone=Coder-Ins., #GT Data=-2026.0527.231.526.532.8
Qwen2.5-14B-CoderBackbone=Coder, #GT Data=-2026.0526.319.56.720.1
AZR-7B-CoderBackbone=Coder, #GT Data=02026.0526.12710.221.9
Seed-Coder-8B-InstructBackbone=-, #GT Data=-2026.0525.225.521.428.2
Qwen2.5-7B-Instruct + ClusterBackbone=Ins., #GT Data=-2026.0524.414.61924.4
AZR-14B-CoderBackbone=Coder, #GT Data=02026.0524.326.225.130.3
AceCoder-7B-RuleBackbone=Coder-Ins., #GT Data=22k2026.0523.613.720.524.8
AceCoder-7B-RMBackbone=Coder-Ins., #GT Data=329k2026.0523.615.120.625.8
Qwen2.5-7B-Coder-Ins.Backbone=Coder-Ins., #GT Data=-2026.0523.510.42024.5
Qwen2.5-7B-CoderBackbone=Coder, #GT Data=-2026.0523.413.3312
Qwen2.5-7B-Instruct + CodeTBackbone=Ins., #GT Data=-2026.0522.914.61922.9
Qwen2.5-7B-InstructBackbone=Ins., #GT Data=-2026.0522.114.61922.1