Scientific Question Answering on MMLU
79.45AccuracyEVOSELECT
Evaluation Results
| Method | Links | |
|---|---|---|
| EVOSELECTIteration=Iter. 1, Selection Ratio=0.2, Model Scale=14b base model2026.04 | 79.45 | |
| Attr-DivIteration=Iter. 2, Selection Ratio=0.2, Model Scale=14b base model2026.04 | 79.28 | |
| RandomIteration=Iter. 1, Selection Ratio=0.2, Model Scale=14b base model2026.04 | 79.22 | |
| EVOSELECTIteration=Iter. 2, Selection Ratio=0.2, Model Scale=14b base model2026.04 | 79.22 | |
| AttributionIteration=Iter. 1, Selection Ratio=0.2, Model Scale=14b base model2026.04 | 79.19 | |
| EVOSELECTIteration=Iter. 1, Selection Ratio=0.5, Model Scale=14b base model2026.04 | 79.18 | |
| RandomIteration=Iter. 2, Selection Ratio=0.2, Model Scale=14b base model2026.04 | 79.18 | |
| DiversityIteration=Iter. 2, Selection Ratio=0.2, Model Scale=14b base model2026.04 | 79.15 | |
| EVOSELECTIteration=Iter. 2, Selection Ratio=0.5, Model Scale=14b base model2026.04 | 79.14 | |
| TSDSIteration=Iter. 2, Selection Ratio=0.2, Model Scale=14b base model2026.04 | 79.13 | |
| TSDSIteration=Iter. 2, Selection Ratio=0.5, Model Scale=14b base model2026.04 | 79.12 | |
| AllIteration=Iter. 1, Model Scale=14b base model2026.04 | 79.11 | |
| AttributionIteration=Iter. 2, Selection Ratio=0.2, Model Scale=14b base model2026.04 | 79.07 | |
| AttributionIteration=Iter. 1, Selection Ratio=0.5, Model Scale=14b base model2026.04 | 79.06 | |
| TSDSIteration=Iter. 1, Selection Ratio=0.2, Model Scale=14b base model2026.04 | 79.03 | |
| DiversityIteration=Iter. 2, Selection Ratio=0.5, Model Scale=14b base model2026.04 | 79.03 | |
| Attr-DivIteration=Iter. 1, Selection Ratio=0.2, Model Scale=14b base model2026.04 | 78.91 | |
| AttributionIteration=Iter. 2, Selection Ratio=0.5, Model Scale=14b base model2026.04 | 78.89 | |
| DiversityIteration=Iter. 1, Selection Ratio=0.2, Model Scale=14b base model2026.04 | 78.86 | |
| Attr-DivIteration=Iter. 1, Selection Ratio=0.5, Model Scale=14b base model2026.04 | 78.86 | |
| BaseModel Scale=14b base model2026.04 | 78.82 | |
| RandomIteration=Iter. 1, Selection Ratio=0.5, Model Scale=14b base model2026.04 | 78.79 | |
| DiversityIteration=Iter. 1, Selection Ratio=0.5, Model Scale=14b base model2026.04 | 78.75 | |
| TSDSIteration=Iter. 1, Selection Ratio=0.5, Model Scale=14b base model2026.04 | 78.75 | |
| RandomIteration=Iter. 2, Selection Ratio=0.5, Model Scale=14b base model2026.04 | 78.66 | |
| AllIteration=Iter. 2, Model Scale=14b base model2026.04 | 78.52 | |
| Attr-DivIteration=Iter. 2, Selection Ratio=0.5, Model Scale=14b base model2026.04 | 78.52 |