40-task evaluation set
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Open-ended scientific discovery | 40-task evaluation set Overall 2025 | Expert Score (ES)4.78 | 5 |
Showing 1 of 1 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Open-ended scientific discovery | 40-task evaluation set Overall 2025 | Expert Score (ES)4.78 | 5 |