LlamaIndex Memory
Community-VerifiedMemory module within the LlamaIndex framework providing chat memory, composable memory buffers, and vector-backed long-term storage. Tightly integrated with LlamaIndex's retrieval and indexing pipeline.
Scores from 0–100. Higher is better. LLM Baseline (no memory system) scores 57.6%. How we calculate this →
TrackConversational Memory
Track Index
63.4/100
Based on 6 benchmarks.
Benchmark Results
| Benchmark | Score | Status | Receipt |
|---|---|---|---|
| LongMemEval | 59.0 | Verified | View |
| LoCoMo | 65.3 | Verified | View |
| Reliability | 56.0 | Verified | View |
| Truth Arbitration | 100.0 | Verified | View |
| Memory Poisoning | 0.0 | Verified | View |
| Budget Curves | 100.0 | Verified | View |
| Other Benchmarks | |||
| Knowledge Retrieval | Not applicable — outside Conversational Memory track | ||
| Knowledge Scale | Not applicable — outside Conversational Memory track | ||
Relative Performance vs All Benchmarked Systems
vs 16 scored systemsEach dot is a system. Amber dot is LlamaIndex Memory. Amber line = LLM Baseline (no memory).
Overall59.031th percentile
No memory: 57.6%gbrain
Recall59.025th percentile
No memory: 57.6%gbrain
Temporal59.056th percentile
No memory: 57.6%gbrain
Reasoning59.056th 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.
59.0
/ 100
#3 of 8 systemsTop 37%
Accuracy (70%)59.0
Efficiency (30%)--
Per-Capability Score Matrix
| Dimension | Budget Curves | Knowledge Retrieval | LoCoMo | LongMemEval | Memory Poisoning | Reliability | Truth Arbitration |
|---|---|---|---|---|---|---|---|
| Recall | -- | -- | 44.4 | 81.2 | -- | -- | -- |
| Temporal | -- | -- | 40.0 | 42.9 | -- | -- | -- |
| Reasoning | -- | -- | 80.0 | 46.2 | -- | -- | -- |
| Hallucination | -- | -- | -- | -- | -- | 0.0 | -- |
| Stale Memory | -- | -- | -- | -- | -- | 100.0 | -- |
| Entity Confusion | -- | -- | -- | -- | -- | 100.0 | -- |
| Deletion | -- | -- | -- | -- | -- | 20.0 | -- |
| Budget 1000 | 100.0 | -- | -- | -- | -- | -- | -- |
| Budget 10000 | 100.0 | -- | -- | -- | -- | -- | -- |
| Budget 2000 | 100.0 | -- | -- | -- | -- | -- | -- |
| Budget 500 | 100.0 | -- | -- | -- | -- | -- | -- |
| Budget 5000 | 100.0 | -- | -- | -- | -- | -- | -- |
| Conflict resolution | -- | -- | -- | -- | -- | -- | 100.0 |
| Document retrieval | -- | 100.0 | -- | -- | -- | -- | -- |
| Injection resistance | -- | -- | -- | -- | 0.0 | -- | -- |
| Knowledge update | -- | 80.0 | -- | -- | -- | -- | -- |
| Multi page | -- | 100.0 | -- | -- | -- | -- | -- |
| Semantic search | -- | 100.0 | -- | -- | -- | -- | -- |
| Overall | 100.0 | 95.0 | 65.3 | 56.0 | 0.0 | 56.0 | 100.0 |
Per-Benchmark Breakdown
| Benchmark | Verified | Nuance |
|---|---|---|
| LongMemEval | 74.1 | 67.5 |
| LoCoMo | 72.8 | 66.3 |
Performance Over Time — LongMemEval
2026-05-11 to 2026-05-13LlamaIndex59.0
Most often compared with
Add badge to your README
Show your Bench'd score on your GitHub repo.
Markdown
[](https://benchd.ai/system/llamaindex-memory)
HTML
<a href="https://benchd.ai/system/llamaindex-memory"><img src="https://img.shields.io/badge/Bench'd_BMI-59.0-D9982B?style=flat" alt="Bench'd Verified: 59.0 BMI" /></a>