List your company

Reasoning on PIQA Clean Setting

84.2AccuracyUSMoE
50.459.17567.9576.725Mar 29, 2025

Evaluation results

MethodLinks
USMoEModel=Qwen3-30B-A3B-Thinking, Evaluation Protocol=0-shot2025.0384.2
OriginalModel=Qwen3-30B-A3B-Thinking, Selection Strategy=Token Choice (TC), Evaluation Protocol=0-shot2025.0381.2
USMoEModel=Qwen3-30B-A3B-Instruct, Evaluation Protocol=0-shot2025.0381
OriginalModel=Qwen3-30B-A3B-Instruct, Selection Strategy=Token Choice (TC), Evaluation Protocol=0-shot2025.0380.5
Expert Choice (EC)Model=Qwen3-30B-A3B-Thinking, Evaluation Protocol=0-shot2025.0364.9
Expert Choice (EC)Model=Qwen3-30B-A3B-Instruct, Evaluation Protocol=0-shot2025.0364.6
MoEEModel=Qwen3-30B-A3B-Instruct, Selection Strategy=Token Choice (TC), Evaluation Protocol=0-shot2025.0352.1
MoEEModel=Qwen3-30B-A3B-Thinking, Selection Strategy=Token Choice (TC), Evaluation Protocol=0-shot2025.0351.7