Long-term memory conversation-based question answering on LoCoMo
97.15Accuracy (Single-Hop)T-Mem
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| T-MemQA Pipeline=HyperMem's own QA pipeline2026.06 | 97.15 | 93.62 | 91.28 | 71.88 | 93.7 | 16.97 | |
| HyperMemQA Pipeline=HyperMem's own QA pipeline2026.06 | 96.08 | 93.62 | 89.72 | 70.83 | 92.73 | 15.78 | |
| T-MemQA Pipeline=Official LoCoMo pipeline2026.06 | 85.97 | 69.15 | 82.55 | 55.21 | 80.26 | 51.96 | |
| HyperMemQA Pipeline=Official LoCoMo pipeline2026.06 | 84.34 | 62.29 | 79.44 | 47.92 | 77.01 | 49.93 | |
| MemOSQA Pipeline=Official LoCoMo pipeline2026.06 | 81.09 | 67.49 | 75.18 | 55.9 | 75.8 | 45.27 | |
| Mem0QA Pipeline=Official LoCoMo pipeline2026.06 | 73.33 | 58.75 | 52.34 | 45.83 | 64.57 | 43.46 | |
| MemobaseQA Pipeline=Official LoCoMo pipeline2026.06 | 73.12 | 64.65 | 81.2 | 53.12 | 72.01 | 50.18 | |
| MIRIXQA Pipeline=Official LoCoMo pipeline2026.06 | 68.22 | 54.26 | 68.54 | 46.88 | 64.33 | 28.1 | |
| SupermemoryQA Pipeline=Official LoCoMo pipeline2026.06 | 67.3 | 51.12 | 31.77 | 42.67 | 55.34 | 34.87 | |
| MemUQA Pipeline=Official LoCoMo pipeline2026.06 | 66.34 | 63.12 | 27.1 | 50 | 56.55 | 35.15 | |
| ZepQA Pipeline=Official LoCoMo pipeline2026.06 | 66.23 | 52.12 | 54.82 | 33.33 | 59.22 | 41.23 |