Long-term memory conversation-based question answering on LoCoMo benchmark leaderboard · SOTA2 Research

Long-term memory conversation-based question answering on LoCoMo

97.15Accuracy (Single-Hop)T-Mem

Evaluation Results

Method	Links
T-Mem2026.06		97.15	93.62	91.28	71.88	93.7	16.97
HyperMem2026.06		96.08	93.62	89.72	70.83	92.73	15.78
T-Mem2026.06		85.97	69.15	82.55	55.21	80.26	51.96
HyperMem2026.06		84.34	62.29	79.44	47.92	77.01	49.93
MemOS2026.06		81.09	67.49	75.18	55.9	75.8	45.27
Mem02026.06		73.33	58.75	52.34	45.83	64.57	43.46
Memobase2026.06		73.12	64.65	81.2	53.12	72.01	50.18
MIRIX2026.06		68.22	54.26	68.54	46.88	64.33	28.1
Supermemory2026.06		67.3	51.12	31.77	42.67	55.34	34.87
MemU2026.06		66.34	63.12	27.1	50	56.55	35.15
Zep2026.06		66.23	52.12	54.82	33.33	59.22	41.23