Humanities Knowledge Evaluation on MMLU Humanities (test)
59.9AccuracyQwen 2.5 7B Instruct
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Qwen 2.5 7B Instructk=42025.09 | 59.9 | 2.6 | 78.5 | 0.78 | |
| Llama 3.1 8B Instructk=42025.09 | 58.6 | 3.4 | 77.9 | 0.47 |
Loading the SOTA2 catalog…