List your company

Reasoning on WinoGrande Corrupt Setting

56AccuracyUSMoE
48.7250.6152.554.39Mar 29, 2025

Evaluation results

MethodLinks
USMoEModel=Qwen3-30B-A3B-Thinking, Evaluation Protocol=0-shot2025.0356
USMoEModel=Qwen3-30B-A3B-Instruct, Evaluation Protocol=0-shot2025.0354.5
MoEEModel=Qwen3-30B-A3B-Thinking, Selection Strategy=Token Choice (TC), Evaluation Protocol=0-shot2025.0352.2
MoEEModel=Qwen3-30B-A3B-Instruct, Selection Strategy=Token Choice (TC), Evaluation Protocol=0-shot2025.0351.8
Expert Choice (EC)Model=Qwen3-30B-A3B-Thinking, Evaluation Protocol=0-shot2025.0351.3
Expert Choice (EC)Model=Qwen3-30B-A3B-Instruct, Evaluation Protocol=0-shot2025.0351.3
OriginalModel=Qwen3-30B-A3B-Instruct, Selection Strategy=Token Choice (TC), Evaluation Protocol=0-shot2025.0349.4
OriginalModel=Qwen3-30B-A3B-Thinking, Selection Strategy=Token Choice (TC), Evaluation Protocol=0-shot2025.0349