List your company

Multi-task Language Understanding on MMLU (Overall, Stem)

61.08Overall AccuracyFrozen Router
53.092855.166457.2459.3136Jun 1, 2026

Evaluation results

MethodLinks
Frozen RouterBackbone=Qwen1.5-MoE-A2.7B, Top-k=42026.0661.0853.19
ProbMoEBackbone=Qwen1.5-MoE-A2.7B, Top-k=42026.0661.0553.82
ConventionalBackbone=Qwen1.5-MoE-A2.7B, Top-k=42026.0661.0353.16
DenseMixerBackbone=Qwen1.5-MoE-A2.7B, Top-k=42026.0661.0352.87
Base ModelBackbone=Qwen1.5-MoE-A2.7B, Top-k=42026.0660.8552.27
ConventionalBackbone=OLMoE-1B-7B, Top-k=82026.0654.0446.46
Frozen RouterBackbone=OLMoE-1B-7B, Top-k=82026.0653.9746.18
DenseMixerBackbone=OLMoE-1B-7B, Top-k=82026.0653.9546.18
ProbMoEBackbone=OLMoE-1B-7B, Top-k=82026.0653.6945.54
Base ModelBackbone=OLMoE-1B-7B, Top-k=82026.0653.444.91