Automated Survey Generation on DeepSurvey Evaluation Topics
8.676Total Score (Weighted)DeepSurvey-Code
Evaluation Results
| Method | Links | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepSurvey-Codeincorporating code repository analysis=true2026.05 | 8.676 | 9.083 | 9.067 | 8.867 | 9 | 9.4 | 8.311 | 8 | 8.933 | 8 | 8.45 | 8.933 | 8.4 | 7.933 | 8.533 | |
| DeepSurvey2026.05 | 8.644 | 9.1 | 9 | 9 | 9 | 9.4 | 8.356 | 8.067 | 8.933 | 8.067 | 8.333 | 8.867 | 8.2 | 8 | 8.267 | |
| AutoSurvey2026.05 | 8.483 | 8.938 | 8.833 | 8.917 | 9 | 9 | 8.417 | 8 | 8.917 | 8.333 | 8.063 | 8.083 | 7.917 | 8.25 | 8 | |
| SurveyForge2026.05 | 8.101 | 8.708 | 8.333 | 9 | 8.917 | 8.583 | 7.795 | 7.636 | 7.833 | 7.917 | 7.646 | 7.583 | 7.75 | 7.75 | 7.5 | |
| LiRARetrieval code=AutoSurvey substitution2026.05 | 8.004 | 8.455 | 8.364 | 8.273 | 8.636 | 8.545 | 7.793 | 7.833 | 7.818 | 7.727 | 7.659 | 8.091 | 7.636 | 7.364 | 7.545 | |
| SurveyXRetrieval code=AutoSurvey substitution2026.05 | 7.244 | 7.667 | 7.933 | 7.333 | 7.533 | 7.867 | 7.222 | 7.667 | 6.8 | 7.2 | 6.833 | 6.933 | 6.333 | 7 | 7.067 |