Benchmark

LongMemEval-S Results

The standard benchmark for AI memory retrieval quality. We publish our full results, methodology, and raw data.

83.6%

Overall accuracy on LongMemEval-S, running gpt-4o-mini

Edging ahead of Supermemory (81.6%) who require more expensive answer models. 10x cheaper for you per query, enabling you to build better systems for lower cost and swap between answer models as needed with no degradation in performance.

Category Breakdown

LongMemEval-S tests six categories of memory retrieval. Each measures a different aspect of how well your memory system understands, stores, and retrieves information.

m3mory
Supermemory
Full context
Zep

Overall

Combined accuracy across all six categories

m3mory
83.6%
Supermemory
81.6%
Full context
60.2%
Zep
71.2%

Single-Session User

Recall facts and details the user has shared in conversation

m3mory
97.1%
Supermemory
97.14%
Full context
81.4%
Zep
92.9%

Single-Session Assistant

Recall information the AI agent itself provided earlier

m3mory
87.5%
Supermemory
96.43%
Full context
94.6%
Zep
80.4%

Single-Session Preference

Recall the user's stated preferences, choices, and decisions

m3mory
86.7%
Supermemory
70.0%
Full context
20.0%
Zep
56.7%

Knowledge Update

Track when information changed without backups or version history, and present the latest fact

m3mory
79.5%
Supermemory
88.46%
Full context
78.2%
Zep
83.3%

Temporal Reasoning

Answer questions that depend on when things happened

m3mory
80.5%
Supermemory
76.69%
Full context
45.1%
Zep
62.4%

Multi-Session

Combine knowledge across multiple conversations to answer a question. The most important metric for agentic AI

m3mory
79.7%
Supermemory
71.43%
Full context
44.3%
Zep
57.9%

Methodology

What is LongMemEval-S?

LongMemEval-S (Short) is a standardised benchmark for evaluating AI memory systems. It tests how accurately a system can store, update, and retrieve information from long-running conversations across six categories.

How we tested

Each system was given identical conversation histories and asked the same retrieval questions. m3mory used gpt-4o-mini for all LLM calls. All competitors used GPT-4o for their answers, a significantly more expensive model.

The cost advantage

m3mory achieves 83.6% accuracy on gpt-4o-mini at roughly 1/10th the per-query cost of competitors running GPT-4o. Our proprietary retrieval pipeline does the heavy lifting, not the LLM.

Where we excel

Single-session user recall (97.1%), single-session preference (86.7%), temporal reasoning (80.5%), and multi-session (79.7%) are our strongest categories. We beat Supermemory overall (83.6% vs 81.6%) and on preference, temporal reasoning, and multi-session. Every single category above 79%. These map directly to the most common real-world use cases. It doesn't matter what model you choose to use, our system still delivers.

Active development

We are continuously improving our retrieval pipeline. New modules are being added regularly to improve accuracy across all categories.