Share your thoughts, 1 month free Claude Pro on usSee more

Fact Consolidation (Single-Hop) on MemoryAgentBench (MAB) FC-SH 262K

93Accuracy

Ablation C (gpt-4o backbone)

Updated 1d ago

Evaluation Results

Method	Links
Ablation C (gpt-4o backbone) 2026.05		93
Headline 2026.05		82
Ablation A (chunk-4096) 2026.05		73
LLM-judgment baseline 2026.05		61
GPT-4o (long-context) 2026.05		60
HippoRAG-v2 (best published) 2026.05		54
BM25 (MAB chunk-512 default) 2026.05		48
Zep / Graphiti (temporal KG) 2026.05		7