Long-context Reasoning on LoCoMo
93.26F1 (Multi Hop)FluxMem
Evaluation Results
| Method | Links | ||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| FluxMemBackbone=GPT-4.1-mini2026.05 | 93.26 | — | 95.64 | — | 90.62 | — | 95.95 | — | — | — | 95.06 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| EverMemOSBackbone=GPT-4.1-mini2026.05 | 91.84 | — | 89.72 | — | 76.04 | — | 96.67 | — | — | — | 93.05 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FluxMemBackbone=Qwen3-30B-A3B-2507-Instruct2026.05 | 91.49 | — | 89.72 | — | 87.5 | — | 96.19 | — | — | — | 93.44 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MIRIXBackbone=GPT-4.1-mini2026.05 | 83.7 | — | 88.39 | — | 65.62 | — | 85.11 | — | — | — | 85.38 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Full ContextBackbone=GPT-4.1-mini2026.05 | 80.5 | — | 71.03 | — | 58.33 | — | 87.99 | — | — | — | 81.23 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| NemoriBackbone=GPT-4.1-mini2026.05 | 77.3 | — | 76.32 | — | 55.21 | — | 87.16 | — | — | — | 81.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LightMemBackbone=GPT-4.1-mini2026.05 | 76.95 | — | 80.37 | — | 57.29 | — | 87.87 | — | — | — | 82.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Full ContextBackbone=Qwen3-30B-A3B-2507-Instruct2026.05 | 69.86 | — | 51.71 | — | 57.29 | — | 87.4 | — | — | — | 74.87 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Mem0Backbone=GPT-4.1-mini2026.05 | 68.2 | — | 56.9 | — | 47.9 | — | 71.4 | — | — | — | 66.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LightMemBackbone=Qwen3-30B-A3B-2507-Instruct2026.05 | 68.09 | — | 50.16 | — | 52.08 | — | 82.76 | — | — | — | 71.36 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MemoryOSBackbone=GPT-4.1-mini2026.05 | 66.67 | — | 55.45 | — | 60.42 | — | 78.95 | — | — | — | 70.65 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MemoryOSBackbone=Qwen3-30B-A3B-2507-Instruct2026.05 | 63.12 | — | 32.09 | — | 48.96 | — | 79.51 | — | — | — | 59.81 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| A-MemBackbone=GPT-4.1-mini2026.05 | 61.35 | — | 71.03 | — | 50 | — | 77.41 | — | — | — | 71.43 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| A-MemBackbone=Qwen3-30B-A3B-2507-Instruct2026.05 | 57.45 | — | 27.73 | — | 43.75 | — | 67.9 | — | — | — | 56.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ZepBackbone=GPT-4.1-mini2026.05 | 53.7 | — | 60.2 | — | 43.8 | — | 66.9 | — | — | — | 61.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| δ-MemBackbone=Qwen3-8B, Memory Configuration=SSW2026.05 | 46.46 | — | 35.36 | — | 20.05 | — | 62.05 | — | — | — | 51.01 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| δ-MemBackbone=Qwen3-8B, Memory Configuration=MSW2026.05 | 45.52 | — | 34.82 | — | 21.21 | — | 62.27 | — | — | — | 50.92 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| δ-MemBackbone=Qwen3-8B, Memory Configuration=TSW2026.05 | 44.35 | — | 34.76 | — | 17.9 | — | 62.66 | — | — | — | 50.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| δ-MemBackbone=Qwen3-4B-Instruct, Memory Configuration=MSW2026.05 | 42.57 | — | 39.31 | — | 18.12 | — | 58.59 | — | — | — | 49.12 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ATOMMEMBackbone=GPT-4o-mini, Fact Extractor=Qwen3-14B, Top-k=10, Tokens (K)=21357.062026.06 | 42.5 | 33.26 | 62.78 | 57.64 | — | — | 56.66 | 49.56 | — | — | — | — | — | — | — | — | — | — | — | — | 78.48 | 68.44 | 66.98 | 64.58 | |
| δ-MemBackbone=Qwen3-4B-Instruct, Memory Configuration=TSW2026.05 | 42.14 | — | 37.2 | — | 13.35 | — | 55.36 | — | — | — | 46.53 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen3-8BBackbone=Qwen3-8B2026.05 | 41.28 | — | 30.43 | — | 14.2 | — | 59.03 | — | — | — | 47.02 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| δ-MemBackbone=Qwen3-4B-Instruct, Memory Configuration=SSW2026.05 | 41 | — | 36.48 | — | 14.08 | — | 56.88 | — | — | — | 47.05 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Qwen3-4B-InstructBackbone=Qwen3-4B-Instruct2026.05 | 38.39 | — | 32.89 | — | 10.77 | — | 48.05 | — | — | — | 40.79 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Context2LoRABackbone=Qwen3-4B-Instruct2026.05 | 37.95 | — | 34.99 | — | 16.75 | — | 60.11 | — | — | — | 48.11 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AdaMemModel=GPT-4.1-mini2026.03 | 37.7 | 32.08 | 55.9 | 42.37 | 25.87 | 21.7 | 44.84 | 40.02 | — | — | 44.65 | 37.92 | — | — | — | — | — | — | — | — | — | — | — | — | |
| MEMORYOSBackbone=GPT-4o-mini, Top-k=10, Tokens (K)=19207.672026.06 | 37.15 | 26.87 | 41.99 | 36.32 | — | — | 49.72 | 43.58 | — | — | — | — | — | — | — | — | — | — | — | — | 66.47 | 60.99 | 34.58 | 51.04 | |
| ATOMMEM-FLATBackbone=GPT-4o-mini, Fact Extractor=Qwen3-14B, Top-k=10, Tokens (K)=722.752026.06 | 37.03 | 29.5 | 56.45 | 48.98 | — | — | 47.08 | 40.4 | — | — | — | — | — | — | — | — | — | — | — | — | 67.66 | 55.67 | 59.5 | 52.08 | |
| LIGHTMEMBackbone=GPT-4o-mini, Top-k=10, Tokens (K)=5021.562026.06 | 36.59 | 27.27 | 47.41 | 41.29 | — | — | 49.3 | 42.45 | — | — | — | — | — | — | — | — | — | — | — | — | 68.97 | 64.89 | 51.09 | 43.75 | |
| LangMemModel=GPT-4.1-mini2026.03 | 36.45 | 28.53 | 42.57 | 35.91 | 28.8 | 23.13 | 44.82 | 38.25 | — | — | 41.76 | 35.1 | — | — | — | — | — | — | — | — | — | — | — | — | |
| MEM0Backbone=GPT-4o-mini, Top-k=10, Tokens (K)=55300.302026.06 | 36.02 | 25.25 | 30.36 | 29.69 | — | — | 54.95 | 44.71 | — | — | — | — | — | — | — | — | — | — | — | — | 78 | 62.41 | 30.53 | 54.17 | |
| GAMModel=GPT-4o-mini2026.04 | 35.88 | 27.96 | 51.96 | 42.26 | 28.12 | 24.51 | 56.58 | 51.18 | — | — | 43.14 | 36.48 | — | — | — | — | — | — | — | — | — | — | — | — | |
| MemUIntervention=false2026.01 | 35.75 | 25.65 | 15.72 | 12.25 | 25.21 | 18.85 | 42.38 | 35.83 | — | — | 34.71 | 28.16 | — | — | — | — | — | — | — | — | — | — | — | — | |
| AmemIntervention=false2026.01 | 35.69 | 30.65 | 11.32 | 10.11 | 32.63 | 26.46 | 21.75 | 15.88 | — | — | 29.95 | 24.38 | — | — | — | — | — | — | — | — | — | — | — | — | |
| GAMModel=Qwen 2.5-7B2026.04 | 35.32 | 25.77 | 48.97 | 39.68 | 21.14 | 17.89 | 54.58 | 48.62 | — | — | 40 | 32.99 | — | — | — | — | — | — | — | — | — | — | — | — | |
| MemUIntervention=true2026.01 | 35.19 | 25.86 | 13.02 | 9.86 | 24.3 | 17.15 | 42.8 | 35.96 | — | — | 34.05 | 27.5 | — | — | — | — | — | — | — | — | — | — | — | — | |
| Mem0Model=GPT-4.1-mini2026.03 | 35.19 | 26.55 | 34.38 | 29.07 | 20.88 | 15.57 | 42.66 | 36.9 | — | — | 38.16 | 32.04 | — | — | — | — | — | — | — | — | — | — | — | — | |
| AdaMemModel=GPT-4o-mini2026.03 | 35.18 | 26.32 | 51.49 | 37.06 | 25.82 | 21.46 | 42.21 | 36.43 | — | — | 41.84 | 33.78 | — | — | — | — | — | — | — | — | — | — | — | — | |
| Context2LoRABackbone=Qwen3-8B2026.05 | 35.18 | — | 35.05 | — | 20.49 | — | 58.92 | — | — | — | 47.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AmemIntervention=true2026.01 | 35.11 | 30.16 | 8.24 | 7.53 | 19.81 | 12.1 | 13.7 | 10.48 | — | — | 21.16 | 15.28 | — | — | — | — | — | — | — | — | — | — | — | — | |
| MemOSIntervention=false2026.01 | 34.69 | 25.82 | 43.42 | 34.92 | 24.77 | 17.43 | 49.86 | 41.17 | — | — | 44.18 | 35.58 | — | — | — | — | — | — | — | — | — | — | — | — | |
| MemOSIntervention=true2026.01 | 33.88 | 25.91 | 55.41 | 47.77 | 28.14 | 21.09 | 46.57 | 39.43 | — | — | 44.94 | 37.55 | — | — | — | — | — | — | — | — | — | — | — | — | |
| LOCOMOModel=Qwen3-14B2026.02 | 33.37 | 24.26 | 31.49 | 16.42 | 13.92 | 11.02 | 25.46 | 24.82 | 49.17 | 35 | 32.42 | 25.02 | — | — | — | — | — | — | — | — | — | — | — | — | |
| GAMModel=Qwen 2.5-14B2026.04 | 33.32 | 25.38 | 50.25 | 39.33 | 20.4 | 18.5 | 57.55 | 50.99 | — | — | 40.38 | 33.55 | — | — | — | — | — | — | — | — | — | — | — | — | |
| MEMFLYModel=Qwen3-14B2026.02 | 30.8 | 23.13 | 29.25 | 24.56 | 14.11 | 11.03 | 42.25 | 35.52 | 26.59 | 25.02 | 33.65 | 28.45 | — | — | — | — | — | — | — | — | — | — | — | — | |
| Mem0Model=GPT-4o-mini2026.03 | 30.6 | 22.5 | 39.6 | 33.57 | 24.21 | 17.28 | 39.69 | 30.6 | — | — | 37.08 | 30.51 | — | — | — | — | — | — | — | — | — | — | — | — | |
| LangMemModel=GPT-4o-mini2026.03 | 30.24 | 21.6 | 28.89 | 23.67 | 26.55 | 21.24 | 35.01 | 29.88 | — | — | 32.31 | 26.55 | — | — | — | — | — | — | — | — | — | — | — | — | |
| δ-MemBackbone=SmolLM3-3B, Memory Configuration=MSW2026.05 | 29.78 | — | 27.15 | — | 19.59 | — | 49.59 | — | — | — | 39.41 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AriGraphModel=Qwen 2.5-14B2026.04 | 29.4 | 18.2 | 6 | 5.01 | 16.87 | 13.65 | 30.68 | 24.38 | — | — | 24.44 | 18.54 | — | — | — | — | — | — | — | — | — | — | — | — | |
| δ-MemBackbone=SmolLM3-3B, Memory Configuration=SSW2026.05 | 29.12 | — | 27.09 | — | 22.57 | — | 49.45 | — | — | — | 39.39 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GAMModel=Llama 3.2-3B2026.04 | 28.74 | 22.35 | 46.12 | 37.24 | 21.18 | 18.33 | 49.02 | 42.18 | — | — | 36.27 | 30.02 | — | — | — | — | — | — | — | — | — | — | — | — | |
| MEMFLYModel=Qwen3-8B2026.02 | 28.24 | 22.76 | 38.39 | 33.64 | 15.43 | 13.81 | 42.09 | 36.57 | 43.79 | 43.14 | 38.62 | 34.51 | — | — | — | — | — | — | — | — | — | — | — | — | |
| δ-MemBackbone=SmolLM3-3B, Memory Configuration=TSW2026.05 | 27.48 | — | 25.34 | — | 17.04 | — | 44.1 | — | — | — | 35.46 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ZepModel=GPT-4.1-mini2026.03 | 26.73 | 17.91 | 20.97 | 17.55 | 21.24 | 16.92 | 39.96 | 35.1 | — | — | 32.4 | 27.09 | — | — | — | — | — | — | — | — | — | — | — | — | |
| Context2LoRABackbone=SmolLM3-3B2026.05 | 26.35 | — | 26.05 | — | 15.41 | — | 48.58 | — | — | — | 37.74 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MEMORYBANKModel=Qwen3-14B2026.02 | 25.97 | 18.16 | 25.37 | 18.76 | 13.52 | 11.69 | 34.92 | 30.6 | 21.94 | 17.56 | 28.16 | 23.08 | — | — | — | — | — | — | — | — | — | — | — | — | |
| AriGraphModel=GPT-4o-mini2026.04 | 25.1 | 12.92 | 8.44 | 6 | 15.32 | 11.53 | 30.93 | 24.52 | — | — | 24.2 | 17.72 | — | — | — | — | — | — | — | — | — | — | — | — | |
| LOCOMOModel=Qwen3-8B2026.02 | 25.09 | 15.73 | 32.82 | 27.14 | 14.47 | 13.35 | 20.18 | 18.39 | 46.77 | 40.81 | 28.62 | 24.22 | — | — | — | — | — | — | — | — | — | — | — | — | |
| ZepModel=GPT-4o-mini2026.03 | 24.57 | 17.28 | 39.96 | 34.02 | 20.43 | 14.04 | 35.46 | 30.06 | — | — | 33.48 | 27.63 | — | — | — | — | — | — | — | — | — | — | — | — | |
| A-MEMModel=Qwen3-8B2026.02 | 24.3 | 16.9 | 34.5 | 23.1 | 13.1 | 12.2 | 38.1 | 33.3 | 31 | 30.1 | 32.76 | 27.58 | — | — | — | — | — | — | — | — | — | — | — | — | |
| MEMGPTModel=Qwen3-14B2026.02 | 24.12 | 15.41 | 25.48 | 19.04 | 13.44 | 12.64 | 34.74 | 32.41 | 27.11 | 24.32 | 28.99 | 25.06 | — | — | — | — | — | — | — | — | — | — | — | — | |
| MEM-0Model=Qwen3-8B2026.02 | 23.04 | 19.74 | 29.65 | 23.16 | 20.63 | 13.75 | 30.46 | 25.62 | 26.02 | 22.48 | 27.8 | 23.11 | — | — | — | — | — | — | — | — | — | — | — | — | |
| SmolLM3-3BBackbone=SmolLM3-3B2026.05 | 22.41 | — | 16.49 | — | 10.87 | — | 29.22 | — | — | — | 24.18 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MEMGPTModel=Qwen3-8B2026.02 | 22.13 | 13.44 | 31.47 | 22.16 | 14.51 | 13.54 | 33.49 | 34.12 | 34.58 | 31.44 | 30.88 | 27.67 | — | — | — | — | — | — | — | — | — | — | — | — | |
| A-MEMModel=Qwen3-14B2026.02 | 21.36 | 14.98 | 23.06 | 18.04 | 12.62 | 11.49 | 35.43 | 30.92 | 26.71 | 25.78 | 28.37 | 24.48 | — | — | — | — | — | — | — | — | — | — | — | — | |
| AriGraphModel=Qwen 2.5-7B2026.04 | 21.32 | 12.3 | 5.51 | 5.25 | 15.1 | 12.4 | 24.44 | 19.49 | — | — | 19.34 | 14.77 | — | — | — | — | — | — | — | — | — | — | — | — | |
| MEMORYBANKModel=Qwen3-8B2026.02 | 21.25 | 14.53 | 30.2 | 21.11 | 11.33 | 10.53 | 32.75 | 26.33 | 30.95 | 30.13 | 29.27 | 23.9 | — | — | — | — | — | — | — | — | — | — | — | — | |
| A-MEMBackbone=GPT-4o-mini, Top-k=10, Tokens (K)=11687.582026.06 | 21.17 | 15.4 | 34.13 | 29.98 | — | — | 33.87 | 27.64 | — | — | — | — | — | — | — | — | — | — | — | — | 54.1 | 43.26 | 34.89 | 32.29 | |
| MEM-0Model=Qwen3-14B2026.02 | 20.98 | 16.27 | 31.5 | 21.73 | 12.7 | 13.22 | 24.7 | 19.14 | 21.01 | 19.84 | 23.86 | 19.02 | — | — | — | — | — | — | — | — | — | — | — | — | |
| LOCOMOBackbone=GPT-4o-mini, Top-k=10, Tokens (K)=827.202026.06 | 20.97 | 11.09 | 34.79 | 15.46 | — | — | 37.81 | 26.23 | — | — | — | — | — | — | — | — | — | — | — | — | 57.07 | 48.58 | 38.01 | 41.67 | |
| AriGraphModel=Llama 3.2-3B2026.04 | 13.99 | 7.83 | 3.72 | 2.69 | 20.1 | 17.74 | 14.63 | 11.67 | — | — | 12.58 | 9.47 | — | — | — | — | — | — | — | — | — | — | — | — | |
| READAGENTModel=Qwen3-8B2026.02 | 13.17 | 9.3 | 34.91 | 27.04 | 8.8 | 7.45 | 26.44 | 24.83 | 29.98 | 28.34 | 25.87 | 22.93 | — | — | — | — | — | — | — | — | — | — | — | — | |
| READAGENTModel=Qwen3-14B2026.02 | 13.16 | 9.61 | 18.12 | 12.33 | 12.16 | 9.25 | 32.83 | 28.35 | 5.96 | 4.2 | 20.63 | 16.75 | — | — | — | — | — | — | — | — | — | — | — | — | |
| MEMORYBANKBackbone=GPT-4o-mini, Top-k=10, Tokens (K)=926.982026.06 | 11.25 | 8.2 | 14.26 | 9.6 | — | — | 17.85 | 12.13 | — | — | — | — | — | — | — | — | — | — | — | — | 46.61 | 28.01 | 34.27 | 23.96 | |
| A-MemModel=GPT-4.1-mini2026.03 | 11.16 | 11.07 | 42.3 | 33.75 | 30.69 | 25.38 | 24.84 | 18.54 | — | — | 26.37 | 20.7 | — | — | — | — | — | — | — | — | — | — | — | — | |
| A-MemModel=GPT-4o-mini2026.03 | 10.89 | 10.8 | 41.31 | 33.03 | 29.97 | 24.84 | 24.3 | 18.09 | — | — | 25.74 | 22.95 | — | — | — | — | — | — | — | — | — | — | — | — | |
| MemGPTModel=GPT-4.1-mini2026.03 | 10.35 | 10.26 | 30.06 | 24.03 | 28.35 | 23.49 | 22.95 | 17.1 | — | — | 22.5 | 17.64 | — | — | — | — | — | — | — | — | — | — | — | — | |
| MemGPTModel=GPT-4o-mini2026.03 | 10.08 | 9.99 | 29.34 | 23.49 | 27.72 | 22.95 | 22.41 | 16.74 | — | — | 21.96 | 17.28 | — | — | — | — | — | — | — | — | — | — | — | — | |
| BM25 RAGBackbone=Qwen3-4B-Instruct, Memory Mechanism=Textual Memory2026.05 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 38.12 | 20.34 | 9.99 | — | 36.68 | 45.47 | — | — | — | — | |
| COCOMComp. Ratio=4×, Backbone=Mistral-7B-v0.22026.02 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 9.93 | 1.87 | 27.08 | 10.34 | 9.55 | — | — | — | — | — | |
| COCOMComp. Ratio=16×, Backbone=Mistral-7B-v0.22026.02 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 11.35 | 1.87 | 25 | 10.11 | 9.55 | — | — | — | — | — | |
| COCOMComp. Ratio=128×, Backbone=Mistral-7B-v0.22026.02 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 12.06 | 1.56 | 30.21 | 8.32 | 8.96 | — | — | — | — | — | |
| Context2LoRABackbone=Qwen3-4B-Instruct, Memory Mechanism=Parametric Memory2026.05 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 37.95 | 34.99 | 16.75 | — | 48.11 | 60.11 | — | — | — | — | |
| DRIFTComp. Ratio=32×, Backbone=Mistral-7B-v0.22026.02 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 36.88 | 23.99 | 33.33 | 80.38 | 57.73 | — | — | — | — | — | |
| DRIFTComp. Ratio=64×, Backbone=Mistral-7B-v0.22026.02 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 34.75 | 16.82 | 42.71 | 74.67 | 53.31 | — | — | — | — | — | |
| DRIFTComp. Ratio=128×, Backbone=Mistral-7B-v0.22026.02 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 30.14 | 17.13 | 36.46 | 72.06 | 50.71 | — | — | — | — | — | |
| DRIFTComp. Ratio=32×, Backbone=Qwen2.5-Instruct-7B2026.02 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 42.55 | 27.73 | 40.62 | 85.49 | 62.79 | — | — | — | — | — | |
| FadeMem2026.01 | — | — | — | — | — | — | — | — | — | — | 29.43 | — | 85.9 | 0.45 | — | — | — | — | — | — | — | — | — | — | |
| Fixed-16K2026.01 | — | — | — | — | — | — | — | — | — | — | 5.17 | — | 78.9 | 0 | — | — | — | — | — | — | — | — | — | — | |
| Full-ContextBackbone=gpt-4o-mini2025.10 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 58.22 | 49.53 | — | 71.41 | 83.01 | — | — | — | — | |
| Full-ContextBackbone=gpt-4.1-mini2025.10 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 92.7 | 71.88 | — | 87.52 | 88.53 | — | — | — | — | |
| ICAEComp. Ratio=4×, Backbone=Mistral-7B-v0.22026.02 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 17.38 | 3.43 | 23.96 | 15.1 | 13.64 | — | — | — | — | — | |
| LangChain2026.01 | — | — | — | — | — | — | — | — | — | — | 25.75 | — | 81.2 | 0 | — | — | — | — | — | — | — | — | — | — | |
| LangMemBackbone=gpt-4o-mini2025.10 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 23.43 | 71.12 | — | 58.1 | 62.23 | — | — | — | — | |
| LangMemBackbone=gpt-4.1-mini2025.10 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 86.92 | 67.71 | — | 78.05 | 74.47 | — | — | — | — | |
| LLMLingua-2Comp. Ratio=3×, Backbone=Mistral-7B-v0.22026.02 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 46.81 | 27.41 | 48.96 | 76.93 | 59.35 | — | — | — | — | — | |
| LLMLingua-2Backbone=Qwen3-4B-Instruct, Memory Mechanism=Textual Memory2026.05 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 39.07 | 30.13 | 10.98 | — | 40.98 | 49.19 | — | — | — | — | |
| Mem02026.01 | — | — | — | — | — | — | — | — | — | — | 28.37 | — | 83.6 | 0 | — | — | — | — | — | — | — | — | — | — | |
| Mem0Backbone=gpt-4o-mini2025.10 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 55.51 | 72.93 | — | 66.88 | 67.13 | — | — | — | — | |
| Mem0Backbone=gpt-4.1-mini2025.10 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 66.47 | 44.79 | — | 62.47 | 62.41 | — | — | — | — |