Reasoning on PIQA Clean Setting
84.2AccuracyUSMoE
Evaluation Results
| Method | Links | |
|---|---|---|
| USMoEModel=Qwen3-30B-A3B-Thinking, Evaluation Protocol=0-shot2025.03 | 84.2 | |
| OriginalModel=Qwen3-30B-A3B-Thinking, Selection Strategy=Token Choice (TC), Evaluation Protocol=0-shot2025.03 | 81.2 | |
| USMoEModel=Qwen3-30B-A3B-Instruct, Evaluation Protocol=0-shot2025.03 | 81 | |
| OriginalModel=Qwen3-30B-A3B-Instruct, Selection Strategy=Token Choice (TC), Evaluation Protocol=0-shot2025.03 | 80.5 | |
| Expert Choice (EC)Model=Qwen3-30B-A3B-Thinking, Evaluation Protocol=0-shot2025.03 | 64.9 | |
| Expert Choice (EC)Model=Qwen3-30B-A3B-Instruct, Evaluation Protocol=0-shot2025.03 | 64.6 | |
| MoEEModel=Qwen3-30B-A3B-Instruct, Selection Strategy=Token Choice (TC), Evaluation Protocol=0-shot2025.03 | 52.1 | |
| MoEEModel=Qwen3-30B-A3B-Thinking, Selection Strategy=Token Choice (TC), Evaluation Protocol=0-shot2025.03 | 51.7 |