Language Understanding on MMLU 3-order
55.2AccuracyRaw
Evaluation Results
| Method | Links | |
|---|---|---|
| RawModel=Llama-3.1-8B2026.03 | 55.2 | |
| MOSAICModel=Llama-3.1-8B2026.03 | 55.1 | |
| ORPOModel=Llama-3.1-8B2026.03 | 54.9 | |
| SFTModel=Llama-3.1-8B2026.03 | 54.7 | |
| In-contextModel=Llama-3.1-8B2026.03 | 52.7 | |
| RawModel=Llama-3.2-3B2026.03 | 50.7 | |
| MOSAICModel=Llama-3.2-3B2026.03 | 49.4 | |
| ORPOModel=Llama-3.2-3B2026.03 | 49.1 | |
| SFTModel=Llama-3.2-3B2026.03 | 49 | |
| In-contextModel=Llama-3.2-3B2026.03 | 47.2 |