---
type: "post"
id: "introducing-frontiermemory-a-new-way-to-evaluate-agent-43a03f"
slug: "introducing-frontiermemory-a-new-way-to-evaluate-agent-43a03f"
title: "Introducing FrontierMemory: a new way to evaluate agent memory through downstream task performance."
description: "Letta has launched FrontierMemory, a continuous benchmark for agent memory."
retrieval_nugget: "Letta has launched FrontierMemory, a continuous benchmark for agent memory."
published_at: "2026-10-21"
updated_at: "2026-10-21"
record_date: "2026-10-21"
date_kind: "published_at"
topics: ["agent-memory"]
entities: ["Letta","FrontierMemory","Letta Dream","Prime Agent","OpenAI Agents SDK","Opus 5.5","GLM-5.3","GPT-6.1 Sol"]
related_patterns: ["company-memory-needs-write-loops","harness-architecture-outlives-model-choice"]
novelty_label: "new_fact"
what_changed: "FrontierMemory introduces a benchmark that evaluates agent-generated memory by its effect on downstream tasks, with model and harness rankings and task-cost results."
prior_refs: ["memory:79ef826c-5556-874b-aa0c-c90d3b6ff4b2","memory:083055ba-38f3-8444-a482-92bfc4fe80c4"]
source_url: "https://frontiermemory.com/"
source_urls: ["https://frontiermemory.com/"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:introducing-frontiermemory-a-new-way-to-evaluate-agent-43a03f"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/introducing-frontiermemory-a-new-way-to-evaluate-agent-43a03f/","markdown":"https://newruntime.com/posts/introducing-frontiermemory-a-new-way-to-evaluate-agent-43a03f.md","json":"https://newruntime.com/posts/introducing-frontiermemory-a-new-way-to-evaluate-agent-43a03f.json"}
---

# Introducing FrontierMemory: a new way to evaluate agent memory through downstream task performance.

## Retrieval answer

Letta has launched FrontierMemory, a continuous benchmark for agent memory.

Letta has launched FrontierMemory, a continuous benchmark for agent memory. It evaluates generated memory by whether it improves an agent’s solve rate on downstream tasks, rather than by recall of facts from prior context.

Agents receive transcripts from earlier task attempts, including successful and failed ones, and generate memory from them. FrontierMemory then tests that memory on coding and knowledge-work tasks drawn from public benchmarks including HarborIndex, DeepSWE, and SkillsBench. Some tasks are modified so that required knowledge exists only in the supplied transcripts. Web browsing and online solution lookup are not allowed; memory generation is capped at six hours.

The current leaderboard lists Opus 5.5 and GLM-5.3 at 73.3%, with average task costs of $2.80 and $3.58. GPT-6.1 Sol is listed at 60.0% and $0.77. For harnesses, Letta Dream is first at 73.3% and $2.80; Prime Agent is second at 60.0% and $3.74.

The published ranking uses the higher downstream solve rate from Opus 5.5 and GPT-6 Sol at maximum reasoning. The source does not establish that these results generalize to arbitrary production workloads, nor does it provide an independent validation of the benchmark design.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Agent Memory](https://newruntime.com/topics/agent-memory.md): Explore the agent-memory topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)