Knowledge Reasoning on K-Cross (val)
43AccuracyPSO-Merging
Evaluation Results
| Method | Links | |
|---|---|---|
| PSO-MergingBackbone=Qwen2.5-1.5B2026.05 | 43 | |
| EvoGMBackbone=Qwen2.5-1.5B2026.05 | 43 | |
| PSO-MergingBase model=Qwen2.5-1.5B2026.05 | 41.5 | |
| CMABackbone=Qwen2.5-1.5B2026.05 | 41.5 | |
| BaseBase model=Qwen2.5-1.5B2026.05 | 41 | |
| Single BestBase model=Qwen2.5-1.5B2026.05 | 41 | |
| BaseBackbone=Qwen2.5-1.5B2026.05 | 41 | |
| Single BestBackbone=Qwen2.5-1.5B2026.05 | 41 | |
| Model SwarmBackbone=Qwen2.5-1.5B2026.05 | 41 | |
| CMABase model=Qwen2.5-1.5B2026.05 | 40.5 | |
| EvoGMBase model=Qwen2.5-1.5B2026.05 | 40.5 | |
| MTLBase model=Qwen2.5-1.5B2026.05 | 39.5 | |
| MTLBackbone=Qwen2.5-1.5B2026.05 | 39.5 | |
| Model SwarmBase model=Qwen2.5-1.5B2026.05 | 39 | |
| DAREBase model=Qwen2.5-1.5B2026.05 | 38 | |
| DAREBackbone=Qwen2.5-1.5B2026.05 | 38 | |
| Task ArithmeticBase model=Qwen2.5-1.5B2026.05 | 37 | |
| TABackbone=Qwen2.5-1.5B2026.05 | 37 | |
| Model SoupBase model=Qwen2.5-1.5B2026.05 | 35.5 | |
| Model SoupBackbone=Qwen2.5-1.5B2026.05 | 35.5 | |
| TIESBase model=Qwen2.5-1.5B2026.05 | 34.5 | |
| TIESBackbone=Qwen2.5-1.5B2026.05 | 34.5 |