| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Persona Discrimination | NeurIPS Cross-conference | Persona Separability (Δ)0.418 | 16 | |
| Scientific Idea Generation | Neurips 2025 | Absolute Novelty Score4.28 | 12 | |
| Limitation Generation | NeurIPS OpenReview critiques (test) | CGT66.45 | 11 | |
| Review Score Generation | NeurIPS 2025 | Avg Review Score4.8 | 10 | |
| Transductive Cognitive Diagnosis | NeurIPS 20 | AUC78.7 | 4 | |
| Cross-Domain Cognitive Diagnosis | NeurIPS 20 | AUC76.31 | 3 | |
| Inductive Cognitive Diagnosis | NeurIPS 20 | AUC76.59 | 3 |