| Synthetic Benchmark 1.0 (test) | OSU-Mem + GF | Hit@222.5 | | 56 | 25d ago |
| tau-bench multi-burst-augmented cache | OSU-Mem + GF | Hit@268 | | 52 | 25d ago |
| FAKEWIKI Indirect | SCORINGMODEL | Recall@1021.6 | | 26 | 2mo ago |
| FAKEWIKI NoiseInjection | SCORINGMODEL | Recall@1063.5 | | 26 | 2mo ago |
| FAKEWIKI RolePlay | SCORINGMODEL | Recall@1063.8 | | 26 | 2mo ago |
| FAKEWIKI Obfuscate | SCORINGMODEL | Recall@1059.5 | | 26 | 2mo ago |
| FAKEWIKI Clean | SCORINGMODEL | Recall@1078.1 | | 26 | 2mo ago |
| DocRED (dev) | DREEAM (student) | F1 Score57.55 | | 14 | 4mo ago |
| Claim-evidence sets (test) | Qwen3-Reranker-8B | MAP54.19 | | 13 | 4mo ago |
| DocRED (test) | DREEAM (student) | F1 Score57.34 | | 13 | 4mo ago |
| Synthetic benchmark B=256 197 episodes, 907 queries | OSU-Mem | Hit@28.4 | | 10 | 25d ago |
| Synthetic benchmark B=128 197 episodes, 907 queries | OSU-Mem | Hit@22.7 | | 10 | 25d ago |
| FEVEROUS 2021 (test) | | Recall@2087.02 | | 10 | 1mo ago |
| FEVER 2018 (test) | DACLR | Recall@2088.48 | | 10 | 1mo ago |
| G-bench Medical | G-reasoner | Recall93.8 | | 10 | 4mo ago |
| G-bench Novel | G-reasoner | Recall87.7 | | 10 | 4mo ago |
| NQ | Qwen3-Emb-4B + Jina reranker | Recall@531.9 | | 9 | 2mo ago |
| 2Wiki | INTRA | Recall@540.7 | | 9 | 2mo ago |
| CORTEXBENCH Comparison | | Hit@546 | | 8 | 25d ago |
| CORTEXBENCH Bridge | | Hit@538.4 | | 8 | 25d ago |
| FEVER frozen 100-client instance (held-out) | FedMark-FM | Accuracy55 | | 7 | 16d ago |
| Factiverse Evaluation Dataset | XLM-RoBERTa-Large (FT) | F1 Score82.16 | | 7 | 1mo ago |
| MR2 | MEVER | Recall@15.9 | | 7 | 4mo ago |
| Mocheg | MEVER | Recall@124.4 | | 7 | 4mo ago |
| ChartCheck | MEVER | Recall@156 | | 7 | 4mo ago |
