Question Answering on LoCoMo (test)
96.08Single-hop ScoreHyperMem
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| HyperMemModel=GPT-4.1-mini2026.05 | 96.08 | 93.62 | 89.72 | 70.83 | 92.73 | |
| MemCog w/o ProactiveModel=GPT-4.1-mini2026.05 | 92.03 | 92.52 | 86.59 | 94 | 92.87 | |
| MemCog (full)Model=GPT-4.1-mini2026.05 | 91.84 | 92.81 | 80.21 | 94.89 | 92.98 | |
| MemCog w/o ProactiveModel=GPT-4o-mini2026.05 | 90.44 | 92.18 | 81.71 | 93.33 | 91.84 | |
| MemCog (full)Model=GPT-4o-mini2026.05 | 90.43 | 93.13 | 80.21 | 94.65 | 92.66 | |
| MemCog w/o Graph OverlayModel=GPT-4.1-mini2026.05 | 88.48 | 92.19 | 81.25 | 93.22 | 91.39 | |
| MemCog w/o Graph OverlayModel=GPT-4o-mini2026.05 | 86.52 | 90.62 | 77.08 | 92.98 | 90.32 | |
| Full ContextModel=GPT-4.1-mini2026.05 | 86.43 | 86.82 | 71.88 | 93.73 | 89 | |
| HyperMemModel=GLM-5.12026.05 | 85.99 | 88.75 | 67.71 | 93.94 | 89.77 | |
| MemCog (full)Model=GLM-5.12026.05 | 85.28 | 91.56 | 76.04 | 92.27 | 89.83 | |
| MemCog w/o ProactiveModel=GLM-5.12026.05 | 84.52 | 92.23 | 73.03 | 91.91 | 89.48 | |
| MemCog w/o Graph OverlayModel=GLM-5.12026.05 | 78.37 | 88.13 | 70.83 | 89.3 | 85.9 | |
| ZEPModel=GPT-4.1-mini2026.05 | 72.34 | 77.26 | 64.58 | 83.49 | 78.94 | |
| A-MemModel=GPT-4.1-mini2026.05 | 71.99 | 74.77 | 58.33 | 79.88 | 76 | |
| HyperMemModel=GPT-4o-mini2026.05 | 71.28 | 85 | 55.21 | 90.61 | 83.69 | |
| Full ContextModel=GLM-5.12026.05 | 69.5 | 38.75 | 51.04 | 89.66 | 72.97 | |
| Full ContextModel=GPT-4o-mini2026.05 | 67.38 | 73.83 | 63.54 | 78.67 | 74.62 | |
| ZEPModel=GPT-4o-mini2026.05 | 67.38 | 73.83 | 63.54 | 78.67 | 74.62 | |
| mem0Model=GPT-4o-mini2026.05 | 67.13 | 55.51 | 51.15 | 72.93 | 66.88 | |
| mem0Model=GPT-4.1-mini2026.05 | 62.41 | 57.32 | 44.79 | 66.47 | 62.47 | |
| A-MemModel=GPT-4o-mini2026.05 | 61.7 | 64.49 | 40.62 | 76.63 | 69.06 | |
| A-MemModel=GLM-5.12026.05 | 48.94 | 27.81 | 36.46 | 72.06 | 56.4 | |
| mem0Model=GLM-5.12026.05 | 46.75 | 76.56 | 57.29 | 80.74 | 56.16 | |
| ZEPModel=GLM-5.12026.05 | 42.55 | 31.56 | 41.67 | 46.25 | 33.25 |