Social Sciences Knowledge Evaluation on MMLU Social Sciences (test)
78.8Accuracy (ACC)Qwen 2.5 7B Instruct
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Qwen 2.5 7B Instructk=42025.09 | 78.8 | 0.2 | 95.9 | 0.72 | |
| Llama 3.1 8B Instructk=42025.09 | 74 | -0.6 | 90.5 | 0.47 |
Loading the SOTA2 catalog…