List your company

Question Answering on LoCoMo (Detailed Hop Metrics)

67.13Single Hop F1Mem0
3.263619.844336.42553.0057Jan 10, 2026Jan 26, 2026Feb 11, 2026Feb 28, 2026Mar 16, 2026Apr 1, 2026Apr 18, 2026

Evaluation results

MethodLinks
Mem0Base Model=gpt-4.1-nano, Reasoning Level=medium2026.0267.13—51.15—55.51—72.93—————————
MemCoTModel=GPT-4.1-mini, Token=2,7902026.0466.42—43.89—60.88—40.88—59.54———————
Mem0gBase Model=gpt-4.1-nano, Reasoning Level=medium, Graph memory enhancement=true2026.0265.71—47.19—58.13—75.71—————————
MemCoT (w/o ψ_z-o)Model=GPT-4.1-mini, Token=1,7072026.0464.58—38.51—38.94—52.81—53.73———————
MemCoTModel=Qwen2.5-7B2026.0463.99—36.34—40.06—33.08—52.01———————
OpenAIBase Model=gpt-4.1-nano, Reasoning Level=medium2026.0263.79—42.92—21.71—62.29—————————
OpenSageBase Model=gpt-4.1-nano, Reasoning Level=medium2026.0263.21—45.89—57.84—76.38—————————
A-Mem*Base Model=gpt-4.1-nano, Reasoning Level=medium2026.0262.23—47.92—23.43—71.12—————————
ZepBase Model=gpt-4.1-nano, Reasoning Level=medium2026.0261.7—41.35—49.31—76.6—————————
Bi-MemBackbone=GPT-4o-mini2026.0153.6847.9939.1731.8154.4441.5630.9926.949.7442.33——————
RAGBackbone=GPT-4o-mini2026.0152.4547.9427.520.1346.0740.3523.2317.9444.6739.33——————
CAMBackbone=GPT-4o-mini2026.0149.9446.6836.6325.3718.8512.922.7118.9339.2533.92——————
Bi-MemBackbone=Qwen2.5-14B-Instruct2026.0148.0742.9532.4225.5344.2129.2918.3816.1142.5135.19——————
RAGBackbone=Qwen2.5-14B-Instruct2026.0147.8742.7926.3819.5430.7825.9714.1610.5238.232.95——————
MEM0Backbone=GPT-4o-mini2026.0147.6538.7238.7227.1348.9340.5128.6421.5845.0835.88——————
A-MEMBackbone=GPT-4o-mini2026.0144.6537.0627.0220.0945.8536.6712.141239.6132.27——————
HeLa-MemBackbone=GPT-4o-mini, GPT-4o, Qwen2.5-3b (Averaged)2026.0443.738.7533.1325.2240.9635.7222.1117.64———————1.25
MEM0Backbone=Qwen2.5-14B-Instruct2026.0142.5835.1531.7324.8228.9626.2415.0311.2835.9929.88——————
LIGHTMEMBackbone=GPT-4o-mini2026.0141.7937.8329.7824.843.7139.7216.8913.9238.4134.32——————
Mem0Model=GPT-4.1-mini, Token=1,7642026.0441.3—30.14—48.91—16.43—34.2———————
A-MemModel=GPT-4.1-mini, Token=2,5202026.0441.02—25.06—51.01—13.22—32.58———————
ZepModel=GPT-4.1-mini, Token=1,6022026.0439.96—26.73—20.97—21.24—32.4———————
A-MemBackbone=GPT-4o-mini, GPT-4o, Qwen2.5-3b (Averaged)2026.0438.933.0926.0418.636.5329.2115.2414.05———————3
MemoryOSBackbone=GPT-4o-mini, GPT-4o, Qwen2.5-3b (Averaged), reproduced=true2026.0438.4532.8432.6125.4235.3328.5319.314.63———————2.25
LoCoMoBackbone=GPT-4o-mini, GPT-4o, Qwen2.5-3b (Averaged)2026.0436.3229.6419.2114.1710.27.7511.0210.64———————5
MemGPTBackbone=GPT-4o-mini, GPT-4o, Qwen2.5-3b (Averaged)2026.0436.1531.0720.6914.9515.2511.869.488.8———————4.5
LIGHTMEMBackbone=Qwen2.5-14B-Instruct2026.0134.9231.2225.4519.6132.0327.715.8111.8131.3727.12——————
A-MEMBackbone=Qwen2.5-14B-Instruct2026.0133.7530.0422.0915.2827.1922.0513.4910.7428.9524.43——————
LONGCONTEXTBackbone=GPT-4o-mini2026.0132.6920.8522.8716.8412.478.867.875.8925.0816.65——————
CAMBackbone=Qwen2.5-14B-Instruct2026.0132.6923.1524.7818.985.212.7115.2512.4524.3717.42——————
MemoryOSModel=Qwen2.5-7B2026.0429.55—21.03—26.26—40.85—33.74———————
MemVerseModel=Qwen2.5-7B2026.0428.12—24.23—25.05—40.33—33.79———————
MemGPTModel=GPT-4.1-mini, Token=16,9772026.0425.59—17.72—19.44—11.29—18.51———————
Mem0Model=Qwen2.5-7B2026.0424.96—20.31—33.16—32.74—28.75———————
SECOMBackbone=Qwen2.5-14B-Instruct2026.0122.2618.7119.1514.2619.5816.315.7513.0120.7117.02——————
RAGModel=Qwen2.5-7B2026.0421.72—8.05—4.89—14.51—13.88———————
LONGCONTEXTBackbone=Qwen2.5-14B-Instruct2026.012113.1718.0913.2110.545.827.314.7117.4111.1——————
Full ContextModel=GPT-4.1-mini, Token=16,9102026.0418.68—25.02—12.04—19.05—18.7———————
EpMemModel=Qwen2.5-7B2026.0417.64—6.35—9.96—2.66—6.63———————
SECOMBackbone=GPT-4o-mini2026.0116.6713.9615.0611.9314.5812.217.2914.7615.9713.25——————
A-MemModel=Qwen2.5-7B2026.0412.73—8.67—6.28—13.86—12.1———————
Full ContextModel=Qwen2.5-7B2026.0410.61—3.39—3.72—8.24—7.38———————
ReadAgentBackbone=GPT-4o-mini, GPT-4o, Qwen2.5-3b (Averaged)2026.048.466.828.746.076.595.026.576.24———————6.38
MemoryBankBackbone=GPT-4o-mini, GPT-4o, Qwen2.5-3b (Averaged)2026.046.335.195.034.284.623.86.215.94———————6.88
MemoryBankModel=GPT-4.1-mini, Token=4322026.045.72—5—5.94—5.16—5.46———————
ENGRAMSource=Patel and Patel [2025]2026.03——————————23.118.321.98.621.1—
KumihoSource=This work2026.03——————————46.235.553.32944.7—
Mem0Source=Zep [2025]2026.03——————————38.728.648.947.740—
Mem0-GraphSource=Zep [2025]2026.03——————————38.124.351.649.340—
MemobaseSource=Memobase [2025]2026.03——————————46.322.964.251.6——
OpenAI MemSource=Zep [2025]2026.03——————————————34—
ZepSource=Zep [2025]2026.03——————————35.719.44249.6——