Scientific Papers
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Scientific Peer-Reviewing | Scientific papers (test) | R0 Score8.7 | 7 | |
| Poster Generation | Scientific Papers | Perplexity (PPL)4.6 | 7 | |
| Scientific ideation | scientific papers Out-of-Domain | Win Rate vs GPT-5.259 | 2 | |
| Scientific ideation | scientific papers In-Domain | Win Rate vs GPT-5.261 | 2 |
Showing 4 of 4 rows