Back to Benchmarks

PerLTQA

PerLTQA: A Personal Long-Term Memory Question Answering Dataset

Benchmark Metadata

PublisherPolyU
VenuearXiv preprint
Evaluation Typeautomatic
Dimensions3
Test Prompts8,593
ScoringHigher is better
Update Frequencyannual
LeaderboardView Leaderboard

What It Measures

  • Personal semantic-memory recall
  • Personal episodic-memory recall
  • Memory-grounded answer accuracy

What It Does Not Measure

  • Generic factual QA
  • Code or math reasoning
  • Latency

All Systems Evaluated(22 systems)

RankSystemScore
#1Tab AITab (Avi Schiffmann)87.8
#2ReplikaLuka, Inc.86.8
#3Pi InflectionInflection AI85.7
#4Limitless PendantLimitless AI (acquired by Meta Dec 2025)85.5
#5Talkie AIMiniMax84.8
#6Second MeMindverse (Shang, Li, et al.)84.6
#7Friend AIFriend84
#8Character AICharacter.AI (Google investment)82.8
#9Bee ComputerBee (acquired by Amazon 2026)82.5
#10Charlie MnemonicGoodAI81.9
#11Pickle AISoul Computer (YC-backed)80.4
#12ParadotWithFeeling.AI76.6
#13Nomi AIGlimpse AI, Inc.75.7
#14KindroidKindroid74.6
#15Personal AIPersonal AI74
#16memUNevaMind-AI73.2
#17MemoryBankInstitute of Software, Chinese Academy of Sciences72.6
#18Copilot MemoryMicrosoft67.9
#19ChatGPT MemoryOpenAI67.7
#20MnemosyneJohns Hopkins / independent (2025)67.7
#21Gemini MemoryGoogle67.4
#22Heyday AIHeyday (shut down 2025)62.9