| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| LongMemEval | Chronos High | Average Score95.6 | 103 | 1d ago | |
| Mem-Gallery | OMNIMEM | F1 Score81 | 35 | 2mo ago | |
| LongMemEval-s | HyMem | Overall Score75 | 12 | 3mo ago | |
| MemBench | EVOLVEMEM | Recall87.5 | 10 | 19d ago | |
| LoCoMo | Hindsight | Accuracy89.6 | 9 | 1mo ago | |
| LongMemEval v0.6.0 (strict) | TM Pro | Accuracy92 | 7 | 27d ago | |
| BEHEMOTH LongMemEval (out-of-distribution) | CluE | Accuracy63.07 | 6 | 1mo ago |
