| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| LoCoMo | Nous | F1 (Multi Hop)55.32 | 174 | 1mo ago | |
| LongMemEval LongConvQA | InfiniPot | SH Score90.3 | 84 | 2mo ago | |
| HotpotQA In-Distribution | QwenLong-L1-32B | Accuracy85.2 | 72 | 4mo ago | |
| LongBench (test) | LingoEDU | HotpotQA7,011 | 69 | 4mo ago | |
| LongBench | HotPotQA Accuracy59.71 | 59 | 25d ago | ||
| 2WikiMultiHopQA (Out-Of-Distribution) | ReMemR1 | Accuracy63.9 | 54 | 4mo ago | |
| LongBench N=162 | F1 Score31.5 | 45 | 2mo ago | ||
| LoCoMo | Mnemis | Single-Hop LLJ Score97.1 | 45 | 2mo ago | |
| DetectiveQA-En | MiA | Accuracy75.5 | 38 | 2mo ago | |
| DetectiveQA-Zh | MiA-RAG | Accuracy80 | 38 | 2mo ago | |
| NarrativeQA | MiA-RAG | F1 Score53.56 | 38 | 4mo ago | |
| En.QA | Logo-PO | SubEM36.75 | 36 | 3mo ago | |
| NarrativeQA | LongMab | SubEM22 | 36 | 3mo ago | |
| MFQA En | LongReward-PO | SubEM29.33 | 36 | 3mo ago | |
| 2WikiMQA | LongMab | SubEM79.5 | 36 | 3mo ago | |
| LongBench V2 | Overall Accuracy56.77 | 33 | 2mo ago | ||
| FRAMES | Avg@4 Score73.54 | 22 | 4mo ago | ||
| HotpotQA | Mean Score65.49 | 21 | 4mo ago | ||
| MuSiQue | LongMab | F1 Score51.02 | 19 | 3mo ago | |
| Clip 128K | RECONTEXT | Accuracy52 | 18 | 22d ago | |
| InfQA 128K | RECONTEXT | Accuracy25 | 18 | 22d ago | |
| NarrQA 128K | RECONTEXT | Accuracy21 | 18 | 22d ago | |
| PopQA 128K | RECONTEXT | Accuracy23 | 18 | 22d ago | |
| HotpotQA 128K | RECONTEXT | Accuracy25 | 18 | 22d ago | |
| TriviaQA 128K | RECONTEXT | Accuracy70 | 18 | 22d ago |
