Temporal Question Answering on LoCoMo
0.6634F1ShardMemo
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| ShardMemoModel=GPT-OSS-120B2026.01 | 0.6634 | — | — | 0.6031 | — | — | |
| LightMEMModel=GPT-4o2026.01 | 0.6466 | — | — | 0.4658 | — | — | |
| LightMEM+AMAModel=GPT-4o2026.01 | 0.6372 | — | — | 0.4595 | — | — | |
| MEMIRBackbone=GPT-4.1-mini2026.05 | 0.635 | — | — | 0.587 | 0.846 | — | |
| MEMORARetriever Type=Semantic Retriever2026.02 | 0.624 | 0.502 | 0.851 | — | — | — | |
| MEMORARetriever Type=Policy Retriever2026.02 | 0.623 | 0.5 | 0.866 | — | — | — | |
| MEMIRBackbone=GPT-4.12026.05 | 0.618 | — | — | 0.557 | 0.863 | — | |
| Nemori+AMAModel=GPT-4o2026.01 | 0.6065 | — | — | 0.5121 | — | — | |
| SimpleMemBackbone=GPT-4.1-mini2026.05 | 0.604 | — | — | 0.534 | 0.807 | — | |
| SimpleMemBackbone=GPT-4.12026.05 | 0.601 | — | — | 0.536 | 0.819 | — | |
| GAMModel=GPT-OSS-120B2026.01 | 0.5952 | — | — | 0.527 | — | — | |
| NEMORIBackbone=GPT-4.12026.05 | 0.592 | — | — | 0.524 | 0.796 | — | |
| Nemori+AMAModel=GPT-4o-mini2026.01 | 0.5914 | — | — | 0.5001 | — | — | |
| NEMORIBackbone=GPT-4.1-mini2026.05 | 0.587 | — | — | 0.507 | 0.773 | — | |
| NemoriModel=GPT-4o-mini2026.01 | 0.5838 | — | — | 0.4862 | — | — | |
| Nemori*2026.02 | 0.577 | 0.502 | 0.776 | — | — | — | |
| O-MemBackbone=GPT-4.12026.05 | 0.5748 | — | — | 0.4976 | — | — | |
| Full Context2026.02 | 0.572 | 0.506 | 0.819 | — | — | — | |
| LightMEM+AMAModel=GPT-4o-mini2026.01 | 0.5597 | — | — | 0.4257 | — | — | |
| NemoriModel=GPT-4o2026.01 | 0.5586 | — | — | 0.473 | — | — | |
| LightMEMModel=GPT-4o-mini2026.01 | 0.5468 | — | — | 0.4077 | — | — | |
| LangMemBackbone=GPT-4.12026.05 | 0.5367 | — | — | 0.4622 | — | — | |
| HeLa-MemModel=GPT-4o, Token Length=1,0362026.04 | 0.5079 | — | — | 0.4454 | — | — | |
| SwiftMemBackbone=GPT-4.1-mini2026.05 | 0.507 | — | — | 0.569 | 0.685 | — | |
| A-MEM+AMAModel=GPT-4o2026.01 | 0.4965 | — | — | 0.3861 | — | — | |
| A-MEMModel=GPT-4o2026.01 | 0.493 | — | — | 0.382 | — | — | |
| Mem02026.02 | 0.489 | 0.42 | 0.66 | — | — | — | |
| RAG2026.02 | 0.486 | 0.428 | 0.548 | — | — | — | |
| LangMem*2026.02 | 0.485 | 0.409 | 0.508 | — | — | — | |
| LangMemBackbone=GPT-4.1-mini2026.05 | 0.485 | — | — | 0.409 | 0.508 | — | |
| MEM0Model=GPT-OSS-120B2026.01 | 0.4764 | — | — | 0.4127 | — | — | |
| HeLa-MemModel=GPT-4o-mini, Token Length=1,0102026.04 | 0.4729 | — | — | 0.4128 | — | — | |
| HIMEMBackbone=GPT-4.12026.05 | 0.468 | — | — | 0.396 | 0.805 | — | |
| A-MEMModel=GPT-OSS-120B2026.01 | 0.462 | — | — | 0.3714 | — | — | |
| A-MemModel=GPT-4o-mini, Token Length=2,5202026.04 | 0.4585 | — | — | 0.3667 | — | — | |
| RAGModel=GPT-OSS-120B2026.01 | 0.4357 | — | — | 0.3726 | — | — | |
| MemoryOSModel=GPT-4o, Token Length=2,0002026.04 | 0.4357 | — | — | 0.3355 | — | — | |
| Mem0Backbone=GPT-4.12026.05 | 0.435 | — | — | 0.367 | 0.607 | — | |
| HIMEMBackbone=GPT-4.1-mini2026.05 | 0.43 | — | — | 0.388 | 0.792 | — | |
| MEMORYOSModel=GPT-OSS-120B2026.01 | 0.424 | — | — | 0.3281 | — | — | |
| A-MemBackbone=GPT-4.12026.05 | 0.422 | — | — | 0.336 | 0.689 | — | |
| MemoryOSModel=GPT-4o-mini, Token Length=2,0002026.04 | 0.4158 | — | — | 0.3599 | — | — | |
| LIGHTMEMModel=GPT-OSS-120B2026.01 | 0.4148 | — | — | 0.3682 | — | — | |
| A-MemBackbone=GPT-4.1-mini2026.05 | 0.403 | — | — | 0.337 | 0.667 | — | |
| Mem0Backbone=GPT-4.1-mini2026.05 | 0.403 | — | — | 0.337 | 0.569 | — | |
| MemoryOSBackbone=GPT-4.12026.05 | 0.398 | — | — | 0.285 | 0.427 | — | |
| A-MemModel=GPT-4o, Token Length=1,2162026.04 | 0.3941 | — | — | 0.3123 | — | — | |
| MemoryOSBackbone=GPT-4.1-mini2026.05 | 0.365 | — | — | 0.274 | 0.377 | — | |
| HeLa-MemModel=Qwen2.5-14b, Token Length=9442026.04 | 0.3608 | — | — | 0.2991 | — | — | |
| A-MEM+AMAModel=GPT-4o-mini2026.01 | 0.347 | — | — | 0.31 | — | — | |
| A-MEMModel=GPT-4o-mini2026.01 | 0.331 | — | — | 0.293 | — | — | |
| MemoryOSModel=Qwen2.5-14b2026.04 | 0.3224 | — | — | 0.2786 | — | — | |
| LightMemModel=Qwen2.5-14b2026.04 | 0.3203 | — | — | 0.277 | — | — | |
| MEM0Model=Qwen2.5-14b2026.04 | 0.2896 | — | — | 0.2624 | — | — | |
| A-MemModel=Qwen2.5-14b, Token Length=1,3002026.04 | 0.2719 | — | — | 0.2205 | — | — | |
| MemGPTModel=GPT-4o-mini2026.01 | 0.2552 | — | — | 0.1944 | — | — | |
| MemGPTModel=GPT-4o-mini, Token Length=16,9772026.04 | 0.2552 | — | — | 0.1944 | — | — | |
| HeLa-MemModel=Qwen2.5-3b, Token Length=1,0722026.04 | 0.2479 | — | — | 0.2135 | — | — | |
| LightMemBackbone=GPT-4.12026.05 | 0.246 | — | — | 0.204 | 0.662 | — | |
| A-MemModel=Qwen2.5-3b, Token Length=1,3002026.04 | 0.2432 | — | — | 0.1974 | — | — | |
| Zep*2026.02 | 0.239 | 0.2 | 0.602 | — | — | — | |
| ZepBackbone=GPT-4.1-mini2026.05 | 0.239 | — | — | 0.2 | 0.602 | — | |
| Vanilla LLMModel=GPT-OSS-120B2026.01 | 0.2286 | — | — | 0.1702 | — | — | |
| MemoryOSModel=Qwen2.5-3b, Token Length=2,0002026.04 | 0.2085 | — | — | 0.1605 | — | — | |
| LightMemBackbone=GPT-4.1-mini2026.05 | 0.206 | — | — | 0.184 | 0.681 | — | |
| LoCoMoModel=GPT-4o-mini2026.01 | 0.1841 | — | — | 0.1477 | — | — | |
| LoCoMoModel=GPT-4o-mini, Token Length=16,9102026.04 | 0.1841 | — | — | 0.1477 | — | — | |
| MemGPTModel=GPT-4o2026.01 | 0.1729 | — | — | 0.1318 | — | — | |
| MemGPTModel=GPT-4o, Token Length=16,9872026.04 | 0.1729 | — | — | 0.1318 | — | — | |
| ReadAgentModel=GPT-4o-mini2026.01 | 0.126 | — | — | 0.0887 | — | — | |
| ReadAgentModel=GPT-4o-mini, Token Length=6432026.04 | 0.126 | — | — | 0.0887 | — | — | |
| LoCoMoBackbone=GPT-4.1-mini2026.05 | 0.12 | — | — | 0.106 | — | — | |
| MemoryBankModel=GPT-4o-mini2026.01 | 0.0968 | — | — | 0.0699 | — | — | |
| MemoryBankModel=GPT-4o-mini, Token Length=4322026.04 | 0.0968 | — | — | 0.0699 | — | — | |
| LoCoMoModel=GPT-4o2026.01 | 0.0909 | — | — | 0.0578 | — | — | |
| LoCoMoModel=GPT-4o, Token Length=16,9102026.04 | 0.0909 | — | — | 0.0578 | — | — | |
| ReadAgentBackbone=GPT-4.1-mini2026.05 | 0.053 | — | — | 0.042 | — | — | |
| ReadAgentModel=GPT-4o2026.01 | 0.0416 | — | — | 0.0319 | — | — | |
| ReadAgentModel=GPT-4o, Token Length=8052026.04 | 0.0416 | — | — | 0.0319 | — | — | |
| LoCoMoModel=Qwen2.5-3b, Token Length=16,9102026.04 | 0.0311 | — | — | 0.0271 | — | — | |
| ReadAgentModel=Qwen2.5-3b, Token Length=7762026.04 | 0.0301 | — | — | 0.0301 | — | — | |
| MemGPTModel=Qwen2.5-3b, Token Length=16,9612026.04 | 0.0294 | — | — | 0.0295 | — | — | |
| MemoryBankModel=GPT-4o2026.01 | 0.0247 | — | — | 0.0243 | — | — | |
| MemoryBankModel=GPT-4o, Token Length=5692026.04 | 0.0247 | — | — | 0.0243 | — | — | |
| MemoryBankModel=Qwen2.5-3b, Token Length=2982026.04 | 0.0172 | — | — | 0.0197 | — | — | |
| DYNA2026.06 | — | — | — | — | — | 0.7382 | |
| DynaGen2026.06 | — | — | — | — | — | 0.7041 | |
| RAG2026.06 | — | — | — | — | — | 0.6492 |