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

Graphiti

Community-Verified
Zep SoftwareWebsiteGitHub(4.2k)DocsLast tested May 16, 2026

Temporal knowledge graph engine for building and querying dynamic, time-aware knowledge graphs from unstructured data. Designed for agentic memory with entity and relationship extraction.

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

TrackKnowledge Graph
Track Index
0.0/100

Based on 3 benchmarks.2 pending.

Benchmark Results

BenchmarkScoreStatusReceipt
Knowledge Retrieval0.0VerifiedView
Knowledge ScalePendingPending--
Truth Arbitration0.0VerifiedView
Budget Curves0.0VerifiedView
ReliabilityPendingPending--
Other Benchmarks
LongMemEvalNot applicable — outside Knowledge Graph track
LoCoMoNot applicable — outside Knowledge Graph track
Memory PoisoningNot applicable — outside Knowledge Graph track

Relative Performance vs All Benchmarked Systems

vs 16 scored systems

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

Overall
No memory: 57.6%
gbrain
65.050th percentile
Recall
No memory: 57.6%
gbrain
80.056th percentile
Temporal
No memory: 57.6%
gbrain
60.056th percentile
Reasoning
No memory: 57.6%
gbrain
72.063th percentile
Bench'd Memory Index
The BMI combines accuracy (70%) and efficiency (30%) into a single production-weighted score. Formula is public and versioned.
65.0
/ 100
#1 of 8 systemsTop 12%
Accuracy (70%)65.0
Efficiency (30%)--

Per-Capability Score Matrix

DimensionBudget CurvesKnowledge RetrievalLongMemEvalMemory PoisoningTruth Arbitration
Recall----0.0----
Temporal----0.0----
Reasoning----0.0----
Budget 10000.0--------
Budget 100000.0--------
Budget 20000.0--------
Budget 5000.0--------
Budget 50000.0--------
Conflict resolution--------0.0
Document retrieval--0.0------
Injection resistance------0.0--
Knowledge update--0.0------
Multi page--0.0------
Semantic search--0.0------
Overall0.00.00.00.00.0

Per-Benchmark Breakdown

BenchmarkVerifiedNuance
LongMemEval84.878.4
LoCoMo83.477.1

Performance Over Time — LongMemEval

2026-05-11 to 2026-05-13
0255075100baseline05-1105-1205-13

Add badge to your README

Show your Bench'd score on your GitHub repo.

Bench'd Verified: 65.0 BMI
Markdown
[![Bench'd Verified: 65.0 BMI](https://img.shields.io/badge/Bench'd_BMI-65.0-D9982B?style=flat&logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAzMiAzMiI+PHJlY3Qgd2lkdGg9IjMyIiBoZWlnaHQ9IjMyIiByeD0iNiIgZmlsbD0iIzExMSIvPjx0ZXh0IHg9IjgiIHk9IjIyIiBmb250LXNpemU9IjIwIiBmb250LWZhbWlseT0ic2VyaWYiIGZpbGw9IiNmZmYiIGZvbnQtd2VpZ2h0PSI2MDAiPkInPC90ZXh0PjwvcHZnPg==)](https://benchd.ai/system/graphiti)
HTML
<a href="https://benchd.ai/system/graphiti"><img src="https://img.shields.io/badge/Bench'd_BMI-65.0-D9982B?style=flat" alt="Bench'd Verified: 65.0 BMI" /></a>

Command Palette

Search for a command to run...