Zero-shot Reasoning on MC9
63.9AccuracyReg. MoE
Evaluation Results
| Method | Links | |
|---|---|---|
| Reg. MoE# train tokens=1T, Active parameters=1B2026.05 | 63.9 | |
| OLMoE# train tokens=5T, Active parameters=1B2026.05 | 63.5 | |
| EMO# train tokens=1T, Active parameters=1B2026.05 | 63.1 | |
| Reg. MoE# train tokens=130B, Active parameters=1B2026.05 | 60.1 | |
| EMO# train tokens=130B, Active parameters=1B2026.05 | 59.1 | |
| Dense# train tokens=130B, Active parameters=1B2026.05 | 54.1 |