| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Research Idea Generation | Expert Evaluation Biotech Domain (test) | Novelty Winrate vs Qwen-14B91.7 | 1 | |
| Research Idea Generation | Expert Evaluation Education Domain (test) | Novelty Winrate vs Qwen80 | 1 | |
| Research Idea Generation | Expert Evaluation Law Domain (test) | Novelty (Winrate vs Qwen)69.2 | 1 |