Selective Question Answering on AbstainQA (test)
13AccuracyEvoGM
Evaluation Results
| Method | Links | |
|---|---|---|
| EvoGMBase model=Qwen2.5-1.5B2026.05 | 13 | |
| Single BestBase model=Qwen2.5-1.5B2026.05 | 11.9 | |
| BaseBase model=Qwen2.5-1.5B2026.05 | 10.1 | |
| CMABase model=Qwen2.5-1.5B2026.05 | 7.8 | |
| Model SwarmBase model=Qwen2.5-1.5B2026.05 | 7.1 | |
| Task ArithmeticBase model=Qwen2.5-1.5B2026.05 | 6 | |
| PSO-MergingBase model=Qwen2.5-1.5B2026.05 | 5.9 | |
| Model SoupBase model=Qwen2.5-1.5B2026.05 | 4.8 | |
| DAREBase model=Qwen2.5-1.5B2026.05 | 4.3 | |
| TIESBase model=Qwen2.5-1.5B2026.05 | 2.8 | |
| MTLBase model=Qwen2.5-1.5B2026.05 | 0.3 |