Research Idea Quality Assessment on 100 ICLR 2026 problem seeds
3.87Mean Quality ScoreIdeaSpark
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| IdeaSpark2026.07 | 3.87 | 0.35 | 88 | |
| Opus-self-genRetrieval=live retrieval2026.07 | 2.57 | 0.55 | 6 | |
| Opus-4.8 (bare)Configuration=bare2026.07 | 2.56 | 0.57 | 6 | |
| GPT-5.5 (bare)Configuration=bare2026.07 | 1 | 0 | 0 |