Personalized Topic Writing on Personalized Deep Research Dataset v1 (test)
0.3458R-1 ScoreGrok-DR
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| Grok-DRApproach Category=Deep Research Agents2026.05 | 0.3458 | 0.1233 | 0.2024 | 6.26 | 8.57 | 6.18 | 7.65 | |
| Gemini-DRApproach Category=Deep Research Agents2026.05 | 0.2788 | 0.1024 | 0.1234 | 5.93 | 8.25 | 5.35 | 6.76 | |
| PDRApproach Category=Personalized2026.05 | 0.2455 | 0.0971 | 0.0964 | 5.24 | 7.9 | 6.29 | 8.51 | |
| Perplexity-DRApproach Category=Deep Research Agents2026.05 | 0.2343 | 0.0948 | 0.1155 | 4.87 | 7.65 | 6.04 | 7.2 | |
| OpenAI-DRApproach Category=Deep Research Agents2026.05 | 0.2286 | 0.0843 | 0.0844 | 5.1 | 7.84 | 5.58 | 7.82 | |
| +SearchApproach Category=Non-personalized2026.05 | 0.2176 | 0.0947 | 0.0974 | 3.89 | 7.3 | 4.86 | 7.14 | |
| Profile PromptingApproach Category=Personalized2026.05 | 0.2157 | 0.0905 | 0.0748 | 4.43 | 7.44 | 5.32 | 6.87 | |
| Zero-shotApproach Category=Non-personalized2026.05 | 0.1986 | 0.086 | 0.0707 | 3.88 | 7.25 | 4.37 | 6.89 | |
| Iterative RAGApproach Category=Personalized2026.05 | 0.1619 | 0.0761 | 0.0579 | 4.48 | 7.45 | 5.78 | 7.95 |