Natural Language Understanding on GLUE (CoLA and RTE Subset)
87.73CoLA AccuracyMoLA(8888)
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MoLA(8888)Model=Llama3.1-8B, TP=2.17 %2025.09 | 87.73 | 89.53 | |
| MoLA(2468)Model=Llama3.1-8B, TP=1.26 %2025.09 | 87.25 | 90.25 | |
| LD-MoLEModel=Llama3.2-3B, TP=3.28 %2025.09 | 86.02 | 88.38 | |
| MoLA(2468)Model=Llama3.2-3B, TP=1.80 %2025.09 | 86 | 89.53 | |
| MoLA(8888)Model=Llama3.2-3B, TP=3.11 %2025.09 | 85.81 | 90.61 | |
| ReMoLEModel=Llama3.1-8B, TP=2.17 %2025.09 | 85.27 | 88.43 | |
| LD-MoLEModel=Llama3.1-8B, TP=2.33 %2025.09 | 85.25 | 91.32 | |
| ReMoLEModel=Llama3.2-3B, TP=3.11 %2025.09 | 83.95 | 89.46 | |
| MoLA(8888)Model=Qwen3-1.7B, TP=4.12 %2025.09 | 83.89 | 86.64 | |
| MoLA(2468)Model=Qwen3-1.7B, TP=2.39 %2025.09 | 83.6 | 84.48 | |
| LD-MoLEModel=Qwen3-1.7B, TP=4.23 %2025.09 | 82.61 | 87.72 | |
| ReMoLEModel=Qwen3-1.7B, TP=4.12 %2025.09 | 82.12 | 83.74 |