Research Soundness Evaluation on 34 report pairs (sample)
70.6Evidence SupportScholarEval
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| ScholarEval2025.10 | 70.6 | 79.4 | 82.4 | |
| OpenAI Deep Research2025.10 | 14.7 | 11.8 | 11.8 | |
| Tie2025.10 | 14.7 | 8.8 | 5.9 |
| Method | Links | |||
|---|---|---|---|---|
| ScholarEval2025.10 | 70.6 | 79.4 | 82.4 | |
| OpenAI Deep Research2025.10 | 14.7 | 11.8 | 11.8 | |
| Tie2025.10 | 14.7 | 8.8 | 5.9 |