STEM Knowledge Evaluation on MMLU STEM (test)
65.2AccuracyQwen 2.5 7B Instruct
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Qwen 2.5 7B Instructk=42025.09 | 65.2 | 0.2 | 89.7 | 0.7 | |
| Llama 3.1 8B Instructk=42025.09 | 54.7 | 0.2 | 91.1 | 0.32 |
| Method | Links | ||||
|---|---|---|---|---|---|
| Qwen 2.5 7B Instructk=42025.09 | 65.2 | 0.2 | 89.7 | 0.7 | |
| Llama 3.1 8B Instructk=42025.09 | 54.7 | 0.2 | 91.1 | 0.32 |