| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| LongMemEval-S (500 questions) | ByteRover | KU Accuracy98.7 | 16 | 1mo ago | |
| ATM-Bench 1.0 (test) | QS77.8 | 15 | 2mo ago | ||
| LoCoMo 0.6.0 | EverMemOS | Accuracy94.48 | 10 | 2mo ago | |
| LOCOMO | VikingMem | SH F1 Score59.59 | 7 | 1mo ago | |
| LongMemEvalS | H-MEM | SSU F178.7 | 7 | 1mo ago | |
| REALTALK (Overall) | H-MEM | Multi-hop F137.41 | 7 | 2mo ago | |
| LoCoMo (overall) | DMF | Average Judge Score77.53 | 4 | 1mo ago | |
| LoCoMo single-hop | Mem0 | Average Judge Score87.16 | 2 | 1mo ago | |
| LoCoMo temporal | DMF | Average Judge Score70.72 | 2 | 1mo ago |