Reasoning on H_Eval
46.95AccuracyBEAM
Evaluation Results
| Method | Links | |
|---|---|---|
| BEAMSparsity Level=Mid Sparsity, beta=0.01, Avg. K=2.612026.05 | 46.95 | |
| DeepSeekV2-LiteK=6, Avg. K=6.002026.05 | 43.9 | |
| BEAMSparsity Level=High Sparsity, beta=0.1, Avg. K=1.082026.05 | 43.29 | |
| BEAMSparsity Level=Extreme Sparsity, beta=1.0, Avg. K=0.482026.05 | 42.07 | |
| Top-K ReducedSparsity Level=Mid Sparsity, K=4, Avg. K=4.002026.05 | 40.85 | |
| MoE-DynamicSparsity Level=High Sparsity, phi=0.1, Avg. K=3.902026.05 | 39 | |
| MoE-DynamicSparsity Level=Mid Sparsity, phi=0.3, Avg. K=4.312026.05 | 38.35 | |
| Top-K PruningSparsity Level=Mid Sparsity, K=4, Avg. K=4.002026.05 | 37.8 | |
| Top-K ReducedSparsity Level=High Sparsity, K=2, Avg. K=2.002026.05 | 34.76 | |
| Top-K PruningSparsity Level=High Sparsity, K=2, Avg. K=2.002026.05 | 28.66 | |
| AdaMoESparsity Level=Mid Sparsity, Null=64, Avg. K=3.252026.05 | 25.67 | |
| Top-K ReducedSparsity Level=Extreme Sparsity, K=1, Avg. K=1.002026.05 | 25 | |
| AdaMoESparsity Level=High Sparsity, Null=128, Avg. K=2.112026.05 | 20.73 |