Coding on MBPP++ (accuracy)
65.87AccuracySpiral
Evaluation Results
| Method | Links | |
|---|---|---|
| SpiralGroup=Qwen3-4B-Base, Category=Base and Expert Models2026.06 | 65.87 | |
| RAMGroup=Qwen3-4B-Base, Category=Merged Models2026.06 | 61.11 | |
| DARE + TIESGroup=Qwen3-4B-Base, Category=Merged Models2026.06 | 60.05 | |
| TIESGroup=Qwen3-4B-Base, Category=Merged Models2026.06 | 59.79 | |
| RESMERGEGroup=Qwen3-4B-Base, Category=Merged Models2026.06 | 58.2 | |
| TAGroup=Qwen3-4B-Base, Category=Merged Models2026.06 | 57.14 | |
| TSV-MergeGroup=Qwen3-4B-Base, Category=Merged Models2026.06 | 56.88 | |
| General-ReasonerGroup=Qwen3-4B-Base, Category=Base and Expert Models2026.06 | 55.29 | |
| GRPOGroup=Qwen3-4B-Base, Category=Base and Expert Models2026.06 | 55.03 | |
| Qwen3-4BGroup=Qwen3-4B-Base, Category=Base and Expert Models2026.06 | 5.03 |