Long-horizon behavior prediction on OminiBehavior E-commerce scenario
86.2AccuracyPraMem
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PraMemBackbone=GPT-OSS-120B, Category=Experiential Memory2026.07 | 86.2 | 27.1 | |
| ProExBackbone=GPT-OSS-120B, Category=Advanced Memory2026.07 | 83.3 | 25.2 | |
| TruncationBackbone=GPT-OSS-120B, Category=No Memory2026.07 | 80.1 | 21.3 | |
| Mem0Backbone=GPT-OSS-120B, Category=Advanced Memory2026.07 | 78.9 | 21.6 | |
| MemOSBackbone=GPT-OSS-120B, Category=Advanced Memory2026.07 | 77.3 | 22 | |
| SummaryBackbone=GPT-OSS-120B, Category=Simple Memory2026.07 | 74.5 | 18.2 | |
| PraMemBackbone=Qwen3.5-35B-A3B, Category=Experiential Memory2026.07 | 74.3 | 21.5 | |
| Long-contextBackbone=GPT-OSS-120B, Category=No Memory2026.07 | 72 | 21.4 | |
| ProExBackbone=Qwen3.5-35B-A3B, Category=Advanced Memory2026.07 | 69.2 | 19.8 | |
| MemOSBackbone=Qwen3.5-35B-A3B, Category=Advanced Memory2026.07 | 67.9 | 19.4 | |
| Mem0Backbone=Qwen3.5-35B-A3B, Category=Advanced Memory2026.07 | 65.9 | 19.3 | |
| RAGBackbone=GPT-OSS-120B, Category=Simple Memory2026.07 | 65.7 | 14.3 | |
| TruncationBackbone=Qwen3.5-35B-A3B, Category=No Memory2026.07 | 65.3 | 18.1 | |
| SummaryBackbone=Qwen3.5-35B-A3B, Category=Simple Memory2026.07 | 64.2 | 16.5 | |
| Long-contextBackbone=Qwen3.5-35B-A3B, Category=No Memory2026.07 | 62.2 | 20.1 | |
| RAGBackbone=Qwen3.5-35B-A3B, Category=Simple Memory2026.07 | 61.3 | 15.8 |