| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| CALCONFLICTBENCH 1.0 (test) | Qwen3-8B | Avg Error Rate (N=1)0.3 | 13 | 4d ago | |
| LTI-Bench Overlap (test) | FadeMem | Consistency76.8 | 4 | 4d ago | |
| LTI-Bench Update (test) | FadeMem | Consistency86.5 | 4 | 4d ago | |
| LTI-Bench Contradiction (test) | FadeMem | Consistency78 | 4 | 4d ago |