Quivr
Community-VerifiedOpinionated RAG for integrating GenAI in apps. Personal AI brain that stores and retrieves documents, conversations, and knowledge with semantic search.
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 Quivr. Amber line = LLM Baseline (no memory).
Overall7.36th percentile
No memory: 57.6%gbrain
Recall5.013th percentile
No memory: 57.6%gbrain
Temporal20.019th percentile
No memory: 57.6%gbrain
Reasoning4.019th 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.
7.3
/ 100
#7 of 8 systemsTop 87%
Accuracy (70%)7.3
Efficiency (30%)--
Per-Benchmark Breakdown
| Benchmark | Verified | Nuance |
|---|
Performance Over Time — LongMemEval
2026-05-11 to 2026-05-13Most often compared with
Add badge to your README
Show your Bench'd score on your GitHub repo.
Markdown
[](https://benchd.ai/system/quivr)
HTML
<a href="https://benchd.ai/system/quivr"><img src="https://img.shields.io/badge/Bench'd_BMI-7.3-D9982B?style=flat" alt="Bench'd Verified: 7.3 BMI" /></a>