datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
locomo-benchmark-results
Logica Mind — LoCoMo Benchmark Results
Reproducible accuracy results for Logica Mind
(open-source agent memory) on LoCoMo, alongside published numbers for other
memory systems — all under the same protocol as the Mem0 paper
(arXiv:2504.19413): gpt-4o-mini as both
answerer and judge, adversarial category excluded, 1,540 scored questions.
Leaderboard (results.csv)
System
LoCoMo J
LLM at write time
Source
Letta (filesystem agent)
74.0%
agent-managed
Letta… See the full description on the dataset page: https://huggingface.co/datasets/rovemark/locomo-benchmark-results.gensyn-rover-role-requirementsro_vsr_results_dubla2ro_vsr_resultsRoVidX_post