Textual Quality Evaluation on Theia E3 (test)
69GLEUProvSyn
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ProvSynbase_model=Llama3.2-3B-Instruct, temperature=1.5, max_tokens=20482025.06 | 69 | 70 | |
| Qwen32025.06 | 50 | 100 | |
| Claude2025.06 | 14 | 100 | |
| ProvSynbase_model=Llama3.2-3B-Instruct, temperature=1.5, max_tokens=20482025.06 | 6 | 100 | |
| GPT2025.06 | 3 | 66 | |
| GPT2025.06 | 1 | 100 | |
| DeepSeek2025.06 | 0 | 51 | |
| Claude2025.06 | 0 | 100 | |
| DeepSeek2025.06 | 0 | 100 | |
| Qwen32025.06 | 0 | 100 |