General Reasoning on M-HellaSwag 30 languages
49.29Macro AccuracyLlama 3.1
Evaluation Results
| Method | Links | |
|---|---|---|
| Llama 3.1Base Model=8B Instruct2026.05 | 49.29 | |
| Cross-Lingual ConsensusBase Model=Llama 3.1 8B Instruct2026.05 | 48.44 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| Llama 3.1Base Model=8B Instruct2026.05 | 49.29 | |
| Cross-Lingual ConsensusBase Model=Llama 3.1 8B Instruct2026.05 | 48.44 |