Long-horizon behavior prediction on OminiBehavior (Overall)
84.7AccuracyPraMem
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PraMemBackbone=GPT-OSS-120B, Category=Experiential Memory2026.07 | 84.7 | 31.6 | |
| ProExBackbone=GPT-OSS-120B, Category=Advanced Memory2026.07 | 77.7 | 26.9 | |
| PraMemBackbone=Qwen3.5-35B-A3B, Category=Experiential Memory2026.07 | 75.6 | 25.3 | |
| Mem0Backbone=GPT-OSS-120B, Category=Advanced Memory2026.07 | 74.7 | 26.4 | |
| SummaryBackbone=GPT-OSS-120B, Category=Simple Memory2026.07 | 74.1 | 24.3 | |
| TruncationBackbone=GPT-OSS-120B, Category=No Memory2026.07 | 73.5 | 24.7 | |
| MemOSBackbone=GPT-OSS-120B, Category=Advanced Memory2026.07 | 73.1 | 26.2 | |
| RAGBackbone=GPT-OSS-120B, Category=Simple Memory2026.07 | 69.1 | 20.9 | |
| Long-contextBackbone=GPT-OSS-120B, Category=No Memory2026.07 | 68.4 | 24.6 | |
| ProExBackbone=Qwen3.5-35B-A3B, Category=Advanced Memory2026.07 | 67.6 | 21.5 | |
| SummaryBackbone=Qwen3.5-35B-A3B, Category=Simple Memory2026.07 | 64.1 | 21.1 | |
| TruncationBackbone=Qwen3.5-35B-A3B, Category=No Memory2026.07 | 63.8 | 20.9 | |
| Mem0Backbone=Qwen3.5-35B-A3B, Category=Advanced Memory2026.07 | 63.8 | 21.7 | |
| MemOSBackbone=Qwen3.5-35B-A3B, Category=Advanced Memory2026.07 | 63.4 | 21.9 | |
| RAGBackbone=Qwen3.5-35B-A3B, Category=Simple Memory2026.07 | 60.5 | 19.4 | |
| Long-contextBackbone=Qwen3.5-35B-A3B, Category=No Memory2026.07 | 60.3 | 21.5 |