Reasoning on BoolQ Corrupt Setting
80.8AccuracyUSMoE
Evaluation results
| Method | Links | |
|---|---|---|
| USMoEModel=Qwen3-30B-A3B-Instruct, Evaluation Protocol=0-shot2025.03 | 80.8 | |
| Expert Choice (EC)Model=Qwen3-30B-A3B-Instruct, Evaluation Protocol=0-shot2025.03 | 74.7 | |
| USMoEModel=Qwen3-30B-A3B-Thinking, Evaluation Protocol=0-shot2025.03 | 72.7 | |
| Expert Choice (EC)Model=Qwen3-30B-A3B-Thinking, Evaluation Protocol=0-shot2025.03 | 62.7 | |
| OriginalModel=Qwen3-30B-A3B-Instruct, Selection Strategy=Token Choice (TC), Evaluation Protocol=0-shot2025.03 | 60 | |
| OriginalModel=Qwen3-30B-A3B-Thinking, Selection Strategy=Token Choice (TC), Evaluation Protocol=0-shot2025.03 | 55.6 | |
| MoEEModel=Qwen3-30B-A3B-Thinking, Selection Strategy=Token Choice (TC), Evaluation Protocol=0-shot2025.03 | 37.8 | |
| MoEEModel=Qwen3-30B-A3B-Instruct, Selection Strategy=Token Choice (TC), Evaluation Protocol=0-shot2025.03 | 37.8 |