MatrixArk Contact

Context memory benchmarks

Measured on the memory benchmarks the field actually uses.

MatrixArk's context engine is built on TemporalStore. We benchmark it head-to-head against the leading memory systems on LOCOMO and LongMemEval using one shared open-source harness — the same reader model and embeddings for every system, scored by an LLM judge — so the comparison is about the memory layer, not the model around it.

Head-to-head

TemporalStore matches or beats OpenViking, led by long-horizon memory.

OpenViking / VikingMem report beating the other memory systems in their own papers and pages, so we benchmark against it as the bar to clear. Same harness, same reader, same embeddings; LLM-judged.

BenchmarkMetricTemporalStoreOpenViking
OverallAnswer accuracy (LLM judge)42%34.7%
LongMemEvalAnswer accuracy38%16%
LOCOMOAnswer accuracy44%44%
LongMemEvalRetrieval hit@k0.980.81
Context packsPrompt tokens at equal qualityLarge reduction vs replaying full history

The gap is widest on LongMemEval — long-horizon, multi-session questions — exactly where time-valid, replayable memory with stale-context blocking pays off. On shorter LOCOMO conversations the two are even.

The landscape

How the context approaches differ.

SystemApproachTemporal & replayOne service
MatrixArk / TemporalStoreAppend-structured temporal store; Context modelNative event-time + replayYes — memory, retrieval, counters, replay
OpenViking / VikingMemEvent/entity memory, L0/L1/L2 layersTemporal layersMemory-focused
Mem0Add/search API, scoped memoriesLimitedNeeds a vector store
Zep / GraphitiBi-temporal knowledge graphBi-temporal graphGraph + retrieval
MemOS / MemoriOS/filesystem-style memoryFile-likeMemory-focused

Method

Fair by construction.

Both systems run behind the same open-source harness: identical reader model and embedding model, the same LOCOMO (multi-session conversation QA) and LongMemEval (long-horizon memory) datasets, and an LLM judge applied uniformly. Only the memory layer differs, so the results isolate the contribution of the store — ingestion, retrieval, freshness, and context-pack assembly.

The enterprise story adds the parts a benchmark cannot show on a laptop: shared-storage throughput under concurrency, five-nines availability, and replayable audit — all on the same engine.

Read more

Full reports and write-ups.

ReportMemory benchmark write-upLOCOMO + LongMemEval, method and numbers. Parityvs OpenViking, in detailHead-to-head parity analysis. Open sourcetemporalstore.ai benchmarksThe full OSS report and token-quota study.