Supermemory
Self-ReportedPersonal knowledge management layer that captures bookmarks, notes, and browsing history into a searchable AI memory. Designed for individuals who want a second brain powered by LLMs.
These scores are self-reported by the vendor and have not been independently verified by Bench'd.
Scores from 0–100. Higher is better. LLM Baseline (no memory system) scores 57.6%. How we calculate this →
TrackKnowledge Brain
Track IndexNo results yet
Benchmark Results
| Benchmark | Score | Status | Receipt |
|---|---|---|---|
| Knowledge Retrieval | Pending | Pending | -- |
| Knowledge Scale | Pending | Pending | -- |
| Truth Arbitration | Pending | Pending | -- |
| Budget Curves | Pending | Pending | -- |
| Reliability | Pending | Pending | -- |
| Other Benchmarks | |||
| LongMemEval | Not applicable — outside Knowledge Brain track | ||
| LoCoMo | Not applicable — outside Knowledge Brain track | ||
| Memory Poisoning | Not applicable — outside Knowledge Brain track | ||
Relative Performance vs All Benchmarked Systems
vs 16 scored systemsEach dot is a system. Amber dot is Supermemory. Amber line = LLM Baseline (no memory).
Overall81.669th percentile
No memory: 57.6%gbrain
Recall85.275th percentile
No memory: 57.6%gbrain
Temporal78.969th percentile
No memory: 57.6%gbrain
Reasoning76.469th percentile
No memory: 57.6%gbrain
Bench'd Memory Index
The BMI combines accuracy (70%) and efficiency (30%) into a single production-weighted score. Formula is public and versioned.
81.6
/ 100
#1 of 8 systemsTop 12%
Accuracy (70%)81.6
Efficiency (30%)--
Per-Benchmark Breakdown
| Benchmark | Verified | Nuance |
|---|