Letta's FrontierMemory leaderboard: Letta Dream tops at 73.3%, beating OpenAI and Claude agents
afurgs · x · 2026-10-28
Letta released new FrontierMemory benchmark results measuring how well agent harnesses improve over time by learning from prior experience data.
Top five harnesses:
- Letta Dream: 73.3%, $2.80 per task
- Prime Agent (Prime Intellect): 60.0%, $3.74
- OpenAI Agents SDK: 40.0%, $0.82 (cheapest)
- Claude Managed Agents: 33.3%, $3.21
- Hermes Agent: 26.7%, $2.79
Letta notes Letta Dream and Prime Agent show the largest gains from learning from prior experience data.
More from coding & agent
- Early users praise DeckWerk after weeks of using it for real talks — vincesitzmann · 2026-10-28
- Agentic video editing goes pro: senior editors 5x output, costs to collapse — dotey · 2026-10-28
- Software is going agent-first: sites, browsers, even a new Rust-like language built for agents — mobileraj · 2026-10-28
- HABIT-Bench: Best agent memory system scores just 33.61% at inferring user habits — SJTU · 2026-10-28
- Regehr's 'Piano Test': would you trust formally verified code with your life? — moyix · 2026-10-28
- Vibe-coded 'AI 浮生记' game satirizes AI startup life with compute black-market trading — vista8 · 2026-10-28