Language Modeling on NLP Standard Suite
2.278CE LossMOE
Evaluation Results
| Method | Links | |
|---|---|---|
| MOEBase Model Params=1.21B, Protocol=Zero-shot2025.12 | 2.278 | |
| VERSATILEFFNBase Model Params=1.21B, Protocol=Zero-shot2025.12 | 2.319 | |
| 6-LOOPBase Model Params=1.21B, Protocol=Zero-shot2025.12 | 2.32 | |
| 4-LOOPBase Model Params=1.21B, Protocol=Zero-shot2025.12 | 2.322 | |
| 2-LOOPBase Model Params=1.21B, Protocol=Zero-shot2025.12 | 2.328 | |
| BASEBase Model Params=1.21B, Protocol=Zero-shot2025.12 | 2.385 | |
| MOEBase Model Params=720.81M, Protocol=Zero-shot2025.12 | 2.411 | |
| 6-LOOPBase Model Params=720.81M, Protocol=Zero-shot2025.12 | 2.43 | |
| VERSATILEFFNBase Model Params=720.81M, Protocol=Zero-shot2025.12 | 2.43 | |
| 4-LOOPBase Model Params=720.81M, Protocol=Zero-shot2025.12 | 2.441 | |
| 2-LOOPBase Model Params=720.81M, Protocol=Zero-shot2025.12 | 2.448 | |
| BASEBase Model Params=720.81M, Protocol=Zero-shot2025.12 | 2.519 | |
| MOEBase Model Params=354.71M, Protocol=Zero-shot2025.12 | 2.585 | |
| VERSATILEFFNBase Model Params=354.71M, Protocol=Zero-shot2025.12 | 2.617 | |
| 6-LOOPBase Model Params=354.71M, Protocol=Zero-shot2025.12 | 2.623 | |
| 4-LOOPBase Model Params=354.71M, Protocol=Zero-shot2025.12 | 2.625 | |
| 2-LOOPBase Model Params=354.71M, Protocol=Zero-shot2025.12 | 2.631 | |
| BASEBase Model Params=354.71M, Protocol=Zero-shot2025.12 | 2.779 |