Code Generation on TACO
17.9Avg@8AERO
Evaluation Results
| Method | Links | |
|---|---|---|
| AEROBackbone=Qwen2.5-7B-Instruct-1M, Time (min)=6.95, FLOPs (PetaFLOP)=2295, p-value=—2026.02 | 17.9 | |
| DAPOBackbone=Qwen2.5-7B-Instruct-1M, Time (min)=7.75, FLOPs (PetaFLOP)=2941, p-value== 0.0342026.02 | 16.2 | |
| GRPOBackbone=Qwen2.5-7B-Instruct-1M, Time (min)=11.66, FLOPs (PetaFLOP)=4488, p-value=< 0.0052026.02 | 15.7 | |
| Base ModelBackbone=Qwen2.5-7B-Instruct-1M, Time (min)=—, FLOPs (PetaFLOP)=—, p-value=< 1e-52026.02 | 9.4 |