Commonsense Reasoning on HellaSwag (EM)
94.6EMKimi-K2 Base
Evaluation Results
| Method | Links | |
|---|---|---|
| Kimi-K2 BaseArchitecture=MoE, Activated Params=32B, Total Params=1043B2026.02 | 94.6 | |
| DeepSeek-V3 BaseArchitecture=MoE, Activated Params=37B, Total Params=671B2026.02 | 88.9 | |
| GLM-5 BaseArchitecture=MoE, Activated Params=40B, Total Params=744B2026.02 | 88.1 | |
| GLM-4.5 BaseArchitecture=MoE, Activated Params=32B, Total Params=355B2026.02 | 87.1 |