llamaindex-memory 0.0 on LoCoMollm-baseline 0.0 on LoCoMomem0-local 0.0 on LongMemEvalmem0-local 0.0 on LongMemEvalllamaindex-memory 0.0 on LongMemEvalllm-baseline 0.0 on LongMemEvallangchain-memory 0.0 on LongMemEvalcognee 0.0 on LongMemEval13 systems independently scored64 systems indexedllamaindex-memory 0.0 on LoCoMollm-baseline 0.0 on LoCoMomem0-local 0.0 on LongMemEvalmem0-local 0.0 on LongMemEvalllamaindex-memory 0.0 on LongMemEvalllm-baseline 0.0 on LongMemEvallangchain-memory 0.0 on LongMemEvalcognee 0.0 on LongMemEval13 systems independently scored64 systems indexed

LangChain Memory

Community-Verified
LangChain IncWebsiteGitHub(98.0k)DocsLast tested May 11, 2026

Built-in memory abstractions within the LangChain framework including buffer, summary, entity, and knowledge-graph memory types. General-purpose conversational memory for chains and agents.

Scores from 0–100. Higher is better. LLM Baseline (no memory system) scores 57.6%. How we calculate this →

TrackConversational Memory
Track Index
57.2/100

Based on 6 benchmarks.

Benchmark Results

BenchmarkScoreStatusReceipt
LongMemEval59.0VerifiedView
LoCoMo51.9VerifiedView
Reliability52.0VerifiedView
Truth Arbitration80.0VerifiedView
Memory Poisoning0.0VerifiedView
Budget Curves100.0VerifiedView
Other Benchmarks
Knowledge RetrievalNot applicable — outside Conversational Memory track
Knowledge ScaleNot applicable — outside Conversational Memory track

Relative Performance vs All Benchmarked Systems

vs 16 scored systems

Each dot is a system. Amber dot is LangChain Memory. Amber line = LLM Baseline (no memory).

Overall
No memory: 57.6%
gbrain
34.019th percentile
Recall
No memory: 57.6%
gbrain
34.019th percentile
Temporal
No memory: 57.6%
gbrain
34.031th percentile
Reasoning
No memory: 57.6%
gbrain
34.044th percentile
Bench'd Memory Index
The BMI combines accuracy (70%) and efficiency (30%) into a single production-weighted score. Formula is public and versioned.
34.0
/ 100
#5 of 8 systemsTop 62%
Accuracy (70%)34.0
Efficiency (30%)--

Per-Capability Score Matrix

DimensionBudget CurvesKnowledge RetrievalLoCoMoLongMemEvalMemory PoisoningReliabilityTruth Arbitration
Recall----35.850.0------
Temporal----24.6100.0------
Reasoning----66.1100.0------
Hallucination----------0.0--
Stale Memory----------100.0--
Entity Confusion----------100.0--
Deletion----------0.0--
Budget 1000100.0------------
Budget 10000100.0------------
Budget 2000100.0------------
Budget 500100.0------------
Budget 5000100.0------------
Conflict resolution------------80.0
Document retrieval--100.0----------
Injection resistance--------0.0----
Knowledge update--80.0----------
Multi page--100.0----------
Semantic search--100.0----------
Overall100.095.051.980.00.052.080.0

Per-Benchmark Breakdown

BenchmarkVerifiedNuance
LongMemEval72.165.6
LoCoMo70.864.3

Performance Over Time — LongMemEval

2026-05-11 to 2026-05-13
0255075100baseline05-1105-1205-13
LangChain80.0

Add badge to your README

Show your Bench'd score on your GitHub repo.

Bench'd Verified: 34.0 BMI
Markdown
[![Bench'd Verified: 34.0 BMI](https://img.shields.io/badge/Bench'd_BMI-34.0-D9982B?style=flat&logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAzMiAzMiI+PHJlY3Qgd2lkdGg9IjMyIiBoZWlnaHQ9IjMyIiByeD0iNiIgZmlsbD0iIzExMSIvPjx0ZXh0IHg9IjgiIHk9IjIyIiBmb250LXNpemU9IjIwIiBmb250LWZhbWlseT0ic2VyaWYiIGZpbGw9IiNmZmYiIGZvbnQtd2VpZ2h0PSI2MDAiPkInPC90ZXh0PjwvcHZnPg==)](https://benchd.ai/system/langchain-memory)
HTML
<a href="https://benchd.ai/system/langchain-memory"><img src="https://img.shields.io/badge/Bench'd_BMI-34.0-D9982B?style=flat" alt="Bench'd Verified: 34.0 BMI" /></a>

Command Palette

Search for a command to run...