Question Answering on SealQA (test)
45.26AccuracyMetaSkill-Evolve
Evaluation Results
| Method | Links | |
|---|---|---|
| MetaSkill-EvolveBackbone=Gemma-4 31B2026.07 | 45.26 | |
| Single-LevelBackbone=Gemma-4 31B2026.07 | 37.21 | |
| Static skillBackbone=Gemma-4 31B2026.07 | 29.41 | |
| No-SkillBackbone=Gemma-4 31B2026.07 | 29.17 |