Aethos X hits 94% on EnterpriseRAG-Bench at 42k files, nearing effective ceiling
rohanpaul_ai · x · 2026-09-22
Codos reports preliminary results: Aethos X scores 94% on Onyx's EnterpriseRAG-Bench (42,587 files; 500k+ synthetic enterprise docs, 500 questions), near the benchmark's estimated ceiling. 5–10 parallel Astra agents achieve 86.03%. The result trades latency and cost for retrieval quality. The team forecasts enterprise memory fully solved by H1 2027 as a foundation for self-improving agents.
More from coding & agent
- Open-source jevmail sorts 1,000 Gmail messages locally in 76 seconds for 3 cents — _AustinCalvert_ · 2026-09-22
- Kos raises $12M from 8VC to build AI finance agents for data center invoices — ahelkky · 2026-09-22
- Harrison Chase on decision models: agentic systems are just good engineering around models — Hacubu · 2026-09-22
- LangSmith Integrates Jev for Cheap Large-Scale Trace Mining That Feeds Directly Into Evals — hwchase17 · 2026-09-22
- Shopify partners with Muse for agentic checkout across all stores — firstadopter · 2026-09-22
- How do you manage access profiles for coding agents across local, staging and review? — radim11 · 2026-09-22