Research Idea Generation on Expert Evaluation Law Domain (test)
69.2Novelty (Winrate vs Qwen)DeepInnovator
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| DeepInnovatorevaluation_mode=Human Expert Annotation2026.02 | 69.2 | 53.8 | 60 | 33.3 | 70 | 45.5 | 76.9 | 50 |
Loading the SOTA2 catalog…