Scientific Ideation
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Scientific Ideation | Scientific Ideation 60 samples human-validated (test) | Novelty3.63 | 9 | |
| Scientific Ideation | Scientific Ideation Out-of-Domain | GPT-5.2 Score59 | 2 |
Showing 2 of 2 rows