Docs K  Search
Docs/Benchmarks
Evaluation

LoCoMo benchmark

91.8% on LoCoMo.

01. LoCoMo score

Hebbrix scores 91.8% on LoCoMo, a benchmark for long-term conversational memory.

02. About the benchmark

LoCoMo evaluates how well a system uses information from long conversations to answer questions. It provides a way to assess conversational memory across multiple sessions. Learn more on the LoCoMo research page.

For earlier evaluation methodology and category breakdowns, see the February 2026 evaluation archive. This archive records a separate historical evaluation.

Ask the docs
reading · this page

Hi! I'm the Hebbrix docs assistant. Ask me anything about this page: setup, code examples, endpoints, pricing, or integrations.