Knowledge Evaluation on MMLU-Redux 2.0 (Original)
42.03AccuracySTOC
Evaluation Results
| Method | Links | |
|---|---|---|
| STOCModel Scale=1.7B, Prompts=5-shot, Freezing Layers=Best reported2026.05 | 42.03 | |
| LAMOLModel Scale=1.7B, Prompts=5-shot, Freezing Layers=Best reported2026.05 | 40.53 | |
| STOCModel Scale=0.6B, Prompts=5-shot, Freezing Layers=Best reported2026.05 | 40.26 | |
| LAMOLModel Scale=0.6B, Prompts=5-shot, Freezing Layers=Best reported2026.05 | 39.04 | |
| NaiveModel Scale=1.7B, Prompts=5-shot, Freezing Layers=Best reported2026.05 | 23.48 | |
| NaiveModel Scale=0.6B, Prompts=5-shot, Freezing Layers=Best reported2026.05 | 21.93 |