# Mnemo Memory — Benchmarks (LongMemEval-S)

> Mnemo Memory on the full LongMemEval-S (n=500): 85.2% on the full LongMemEval-S under the official LongMemEval judge (gpt-4o-mini), US-hosted and model-agnostic. Search API ~150ms warm (p50) on live prod /v1/search. Transparent per-category breakdown — multi-session is the lowest category.

Canonical URL: https://mnemohq.com/benchmarks

Mnemo Memory scores 85.2% (426/500) on the full LongMemEval-S benchmark under the official LongMemEval judge prompts with a gpt-4o-mini judge. A conservative cross-check under a strict score==1.0 exact-match gate gives 80.8% (404/500). US-hosted and model-agnostic. The Search API runs a consistent ~150ms warm (p50) on live production /v1/search.

## Per-category results (official LongMemEval judge)

- single-session-user: 95.7%
- single-session-assistant: 87.5%
- knowledge-update: 85.9%
- temporal-reasoning: 86.5%
- multi-session: 77.4% — current bottleneck
- single-session-preference: 83.3%
- Overall: 85.2%

## Two latencies, not to be conflated

SEARCH (the /v1/search product) is a consistent ~150ms warm p50. ANSWER generation — optional LLM synthesis on top — is 3.6s median in fast mode. The retrieval path embeds the query with text-embedding-3-small, then runs hybrid search in parallel (pgvector HNSW vector, Postgres full-text keyword, and fact-aware signals) fused with Reciprocal Rank Fusion, returning ranked memories with citations.

## Retrieval recall

Recall@5 is 99.2% (496/500) on LongMemEval-S with a top-50 candidate pool and no LLM reranker. At five chunks recall is already 98.0%; widening the pool tenfold to fifty chunks moves it by 1.2 points.

## Explore Mnemo

- [Mnemo API documentation](https://mnemohq.com/docs)
- [Pricing](https://mnemohq.com/pricing)
- [Benchmarks](https://mnemohq.com/benchmarks)
- [Company Brain for Slack](https://mnemohq.com/brain)
- [Ask Mnemo widget](https://mnemohq.com/widget)
- [Data-source connectors](https://mnemohq.com/connectors)
- [Framework integrations](https://mnemohq.com/integrations)
- [Trust and security](https://mnemohq.com/trust)
- [Contact](https://mnemohq.com/contact)
- [llms.txt](https://mnemohq.com/llms.txt)
- [OpenAPI 3.1 specification](https://mnemohq.com/openapi.json)

---

This is the Markdown representation of https://mnemohq.com/benchmarks, served by content negotiation on `Accept: text/markdown`. Machine-readable index: https://mnemohq.com/llms.txt · https://mnemohq.com/openapi.json · https://mnemohq.com/sitemap.xml