Code Generation on CodeForces (test)
15.3Sig. ScoreCURE-14B + CoSPlay
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| CURE-14B + CoSPlayBackbone=Ins., #GT Data=4.5k2026.05 | 15.3 | 89.4 | 19.1 | 32.5 | |
| CURE-14B + CoSPlay w/ ClusterBackbone=Ins., #GT Data=4.5k2026.05 | 15.3 | 89.4 | 19.1 | 32.6 | |
| CURE-14BBackbone=Ins., #GT Data=4.5k2026.05 | 14.9 | 77.5 | 12 | 26.1 | |
| CURE-7B + CoSPlay w/ ClusterBackbone=Ins., #GT Data=4.5k2026.05 | 14.4 | 85.6 | 11.1 | 23.1 | |
| Qwen2.5-14B-Ins. + CoSPlayBackbone=Ins., #GT Data=02026.05 | 14.3 | 86.1 | 11.8 | 24.7 | |
| Qwen2.5-14B-Ins. + CoSPlay w/ ClusterBackbone=Ins., #GT Data=02026.05 | 14.3 | 86.1 | 11.8 | 24.6 | |
| CURE-7B + CoSPlayBackbone=Ins., #GT Data=4.5k2026.05 | 14.2 | 85.6 | 11.1 | 23.1 | |
| DeepSeek-Coder-V2-16BBackbone=-, #GT Data=-2026.05 | 13.8 | 37.2 | 6.5 | 16.8 | |
| Qwen2.5-7B-Ins. + CoSPlay w/ ClusterBackbone=Ins., #GT Data=02026.05 | 13.6 | 85 | 6.8 | 16.8 | |
| Qwen2.5-7B-Ins. + CoSPlayBackbone=Ins., #GT Data=02026.05 | 13.3 | 85 | 6.8 | 16.8 | |
| CURE-7BBackbone=Ins., #GT Data=4.5k2026.05 | 11.5 | 46.6 | 7.5 | 16.1 | |
| Qwen2.5-14B-Instruct + CodeTBackbone=Ins., #GT Data=-2026.05 | 10.5 | 22.6 | 7.3 | 13.5 | |
| Qwen2.5-14B-CoderBackbone=Coder, #GT Data=-2026.05 | 10.2 | 16.7 | 2.1 | 9.3 | |
| Qwen2.5-14B-InstructBackbone=Ins., #GT Data=-2026.05 | 9.9 | 22.6 | 7.3 | 13.3 | |
| Qwen2.5-14B-Instruct + ClusterBackbone=Ins., #GT Data=-2026.05 | 9.1 | 22.6 | 7.3 | 13.6 | |
| AZR-14B-CoderBackbone=Coder, #GT Data=02026.05 | 8.5 | 18.9 | 9.5 | 16.2 | |
| Seed-Coder-8B-InstructBackbone=-, #GT Data=-2026.05 | 8.4 | 17 | 6.4 | 10.5 | |
| Qwen2.5-14B-Coder-Ins.Backbone=Coder-Ins., #GT Data=-2026.05 | 7.9 | 18.1 | 5.6 | 9.6 | |
| Qwen2.5-7B-Instruct + CodeTBackbone=Ins., #GT Data=-2026.05 | 7.6 | 12.9 | 5 | 7.6 | |
| AZR-7B-CoderBackbone=Coder, #GT Data=02026.05 | 7.6 | 16.9 | 5.3 | 8.4 | |
| Qwen2.5-7B-InstructBackbone=Ins., #GT Data=-2026.05 | 7.1 | 12.9 | 5 | 7.1 | |
| Qwen2.5-7B-Instruct + ClusterBackbone=Ins., #GT Data=-2026.05 | 7.1 | 12.9 | 5 | 7.1 | |
| Qwen2.5-7B-Coder-Ins.Backbone=Coder-Ins., #GT Data=-2026.05 | 6.9 | 5.3 | 5.4 | 7.9 | |
| Qwen2.5-7B-CoderBackbone=Coder, #GT Data=-2026.05 | 6.8 | 6.7 | 1.8 | 3.5 | |
| AceCoder-7B-RMBackbone=Coder-Ins., #GT Data=329k2026.05 | 6.6 | 6.6 | 5.2 | 7.8 | |
| AceCoder-7B-RuleBackbone=Coder-Ins., #GT Data=22k2026.05 | 6.4 | 5.9 | 5.4 | 7.7 |