Interactive agentic task completion on MemoryArena
68Bundled Web Shop PSDeMem
Evaluation Results
| Method | Links | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeMem2026.05 | 68 | 8 | 3 | 5 | 52 | 27 | 16 | 29 | 39 | 55 | 67 | 24 | — | |
| Long ContextBackbone=4.1-mini2026.05 | 64 | 6 | 0 | 2 | 44 | 4 | 4 | 23 | 33 | 46 | 58 | 16 | — | |
| RAGAggregate=Avg2026.05 | 54 | 0 | 0 | 2 | 49 | 19 | 11 | 26 | 38 | 53 | 65 | 20 | — | |
| Mem02026.05 | 45 | 0 | 0 | 0 | 24 | 24 | 9 | 19 | 34 | 25 | 43 | 14 | — | |
| LightMem2026.06 | 38.3 | — | — | — | — | — | — | — | — | — | — | — | 15.5 | |
| DCI-Lite2026.06 | 33.3 | — | — | — | — | — | — | — | — | — | — | — | 18.8 | |
| MemRL2026.06 | 33.3 | — | — | — | — | — | — | — | — | — | — | — | 14.4 | |
| Long context2026.06 | 32.8 | — | — | — | — | — | — | — | — | — | — | — | 12.8 | |
| HippoRAG2026.06 | 31.7 | — | — | — | — | — | — | — | — | — | — | — | 18.8 | |
| DCI-Lite+Sum2026.06 | 30.6 | — | — | — | — | — | — | — | — | — | — | — | 18.4 | |
| AMA-Agent2026.06 | 30 | — | — | — | — | — | — | — | — | — | — | — | 18 | |
| Mem-T2026.06 | 30 | — | — | — | — | — | — | — | — | — | — | — | 18.4 | |
| PlugMem2026.06 | 28.3 | — | — | — | — | — | — | — | — | — | — | — | 17.7 | |
| SimpleMem2026.06 | 26.7 | — | — | — | — | — | — | — | — | — | — | — | 17.7 |