Mem

Memory systems, readers, and writers.

3 studies
6 comparisons
189 original files

All memory comparisons

Complete + bound counts complete answers with source-matched quotes. Each row is a separate test.

Memory comparison overview
Comparison	Complete + bound	Resources	Evidence scale
Readers · fixed-context replay → Luna / DeepSeek Flash 1017	DeepSeek Flash 101711/13 Luna medium11/13	$0.004811–$0.0193694.54–5.05 s / request	13 inputs / profile2 profiles · one pass
Readers · fixed-context replay → Luna reasoning effort	Luna low10/13 Luna medium11/13 Luna none11/13	$0.004149–$0.0047273.63–4.95 s / request	13 inputs / profile3 profiles · one pass
Systems · native retrieval → Native memory systems Viewing	OpenViking11/13 RAGFlow rc111/13	$0.006922–$0.024261Time: withheld from comparison	13 inputs / profile2 profiles · one pass
Systems · nightly version check → Native memory systems	RAGFlow nightly11/13	Cost not reported4.74 s / request	13 inputs / profile1 profile · one pass
Writers · extraction replay → Luna / DeepSeek Flash 1017	Quality not measuredDeepSeek Flash 1017 · Luna medium	$0.001142–$0.0029144.57–8.31 s / request	3 inputs / profile2 profiles · one pass
Writers · extraction replay → Luna reasoning effort	Quality not measuredLuna low · Luna medium · Luna none	$0.000709–$0.0011203.52–7.72 s / request	4 inputs / profile3 profiles · one pass

Separate tests · no combined ranking.

说明

Costs are workload totals in USD; resource ranges span profiles within that row. Quote binding does not establish semantic entailment.

Systems · native retrieval

Native memory systems · Native retrieval + shared reader

↑ All comparisons

Refine comparison

Study

Test

13 inputs / profile · 2 profiles · October 15, 2026

Test method

Compare complete, source-bound answers first, then the resources used.

Results & evidence ↓

Complete + bound

Answers · higher is better

OpenViking11/13
RAGFlow rc111/13

Settled cost

USD / test · lower is better

OpenViking$0.024261
RAGFlow rc1$0.006922

Time: withheld from comparison.

Results and evidence

Sort columns. Open Details for the profile and original record.

Expand a row for all metrics

Sort

Metric

October 15 · native retrieval. Values are specific to this test. Formal ingestion, retrieval, and reader calls. Calibration is excluded. Platforms and actual context sizes differ; time is withheld from this comparison.
Profile version						Evidence	Details
OpenViking0.5.0	11/13	11/13	30/30	—	$0.024261	Result evidence OpenViking October 15 · native retrieval · 13 inputs per profile Profile Complete + bound answers Cost USD total OpenVikingSelected 11/13 $0.024261 RAGFlow rc1 11/13 $0.006922 Complete + bound requires a complete answer and exact quote binding. Other test groups remain separate. All recorded measures Complete answers 11/13 Complete + bound answers 11/13 Quotes matched 30/30 Time s · mean Withheld from comparison Cost USD total $0.024261415 Configuration & original record Recorded date 2026-10-15 Version 0.5.0 Reader openai/gpt-6-luna Effort medium Embedding Qwen3-Embedding-8B · Nebius · 4096 dimensions Platform AMD64 ingestion; ARM64 recovery Native retrieval + shared reader Formal ingestion, retrieval, and reader calls. Calibration is excluded. Platforms and actual context sizes differ; time is withheld from this comparison. One diagnostic pass with real provider calls. Sort order is descriptive. Source binding alone does not establish semantic support. Open original results-summary.json ↗
RAGFlow rc11.0.0-rc1	11/13	11/13	26/26	—	$0.006922	Result evidence RAGFlow rc1 October 15 · native retrieval · 13 inputs per profile Profile Complete + bound answers Cost USD total OpenViking 11/13 $0.024261 RAGFlow rc1Selected 11/13 $0.006922 Complete + bound requires a complete answer and exact quote binding. Other test groups remain separate. All recorded measures Complete answers 11/13 Complete + bound answers 11/13 Quotes matched 26/26 Time s · mean Withheld from comparison Cost USD total $0.006921865 Configuration & original record Recorded date 2026-10-15 Version 1.0.0-rc1 Reader openai/gpt-6-luna Effort medium Embedding Qwen3-Embedding-8B · Nebius · 4096 dimensions Storage Elasticsearch; seven services Native retrieval + shared reader Formal ingestion, retrieval, and reader calls. Calibration is excluded. Platforms and actual context sizes differ; time is withheld from this comparison. One diagnostic pass with real provider calls. Sort order is descriptive. Source binding alone does not establish semantic support. Open original results-summary.json ↗

One pass · — Withheld from comparison.

说明

USD totals are rounded to 6 decimals. The value tooltip and original record retain the recorded precision. Sorting is descriptive.

Formal ingestion, retrieval, and reader calls. Calibration is excluded. Platforms and actual context sizes differ; time is withheld from this comparison.

Recorded finding

OpenViking and RAGFlow rc1: 11/13 complete + bound. The RAGFlow nightly version check is separate; workloads are not pooled.

Protocol and metric definitions

Same six documents, eight conversation records, two projects, and 13 questions. Each native system supplies context to the same Luna reader.

Synthetic inputs · real provider calls · one pass · no repeated-trial interval.

Complete + bound: complete answer with every quote matched to its supplied source. Complete: complete answers, before quote binding. Quotes: matched / emitted quotes, with a separate denominator. Source binding alone does not establish semantic entailment.

Full conditions and limitations

Results