List your company

MemoryBench Task on MemoryBench Long-Input-Short-Output

52.6Norm-ScoreUNO
24.509631.802339.09546.3877Feb 6, 2026

Evaluation results

MethodLinks
UNOModel=phi-4, Method Type=Training2026.0252.618.4
UNOModel=Qwen3-8B, Method Type=Training2026.0249.9913.49
SFT w/ UNO DataModel=Qwen3-8B, Method Type=Training2026.0248.87
EmbeddingModel=Qwen3-8B, Method Type=RAG2026.0248.4112.29
BM25Model=Qwen3-8B, Method Type=RAG2026.0248.410.87
A-MemModel=Qwen3-8B, Method Type=Memory2026.0247.945.91
UNO-SingleModel=phi-4, Method Type=Training2026.0247.161.93
MemOSModel=Qwen3-8B, Method Type=Memory2026.0247.14-12.16
DPO w/ UNO DataModel=Qwen3-8B, Method Type=Training2026.0247.142.3
BaseModel=Qwen3-8B, Method Type=Baseline2026.0246.946.02
UNO-SingleModel=Qwen3-8B, Method Type=Training2026.0246.815.34
BaseModel=phi-4, Method Type=Baseline2026.0246.46-1.59
ReMemModel=Qwen3-8B, Method Type=Memory2026.0243.78-7.7
BM25Model=phi-4, Method Type=RAG2026.0243.26-15.07
EmbeddingModel=phi-4, Method Type=RAG2026.0242.91-9.62
MemOSModel=phi-4, Method Type=Memory2026.0242.83-26.43
A-MemModel=phi-4, Method Type=Memory2026.0239.69-34.26
SFT w/ UNO DataModel=phi-4, Method Type=Training2026.0238.97-30.81
ReMemModel=phi-4, Method Type=Memory2026.0238.78-35.81
MemoryOSModel=Qwen3-8B, Method Type=Memory2026.0238.51-24.87
DPO w/ UNO DataModel=phi-4, Method Type=Training2026.0232.59-54.2
MemoryOSModel=phi-4, Method Type=Memory2026.0225.59-89.25