| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| BESPOKE | P-CHECK | R-L9.94 | 18 | 1mo ago | |
| OmniPBench | CLIP-I Score0.832 | 12 | 1mo ago | ||
| LongLaMP Pair A Writing (test) | SPECSTEER | ROUGE-130.79 | 8 | 1mo ago | |
| LongLaMP (Pair A) - Review (test) | SPECSTEER | ROUGE-133.03 | 8 | 1mo ago | |
| LongLaMP (Pair A) - Abstract (test) | SPECSTEER | ROUGE-141.35 | 8 | 1mo ago | |
| PersonaMem 128K memory corpus 1.0 (test) | Recol. | Revisit Reasons81.41 | 5 | 1mo ago | |
| PersonaMem 32K memory corpus 1.0 (test) | Recol. | Revisit Reasons94.95 | 5 | 1mo ago | |
| PersonaMem 1M memory corpus 1.0 (test) | RF-Mem | Revisit Reasons77.87 | 4 | 1mo ago |