Glean beats Claude in customer eval: 30% cheaper with better quality, saving $500K a year in tokens
verrsane · x · 2026-09-18
- A real enterprise procurement case: after running evals comparing Claude vs Glean on cost and quality, a client actually increased their Glean contract by six figures.
- Key numbers: Glean was 30% cheaper with better quality, saving the client about $500K per year in token costs.
- The poster's takeaway: "who said RAG is dead" — for enterprise knowledge retrieval, a specialized RAG product can still beat general LLM-based approaches on cost-effectiveness.
More from Companies & People
- Notion CEO Ivan Zhao on Engelbart, Lego, and building tools with an artist's care — ivanhzhao · 2026-09-18
- Savant Lab opens 10 desks to outside physical AI founders in San Francisco — TarlonKhoubyari · 2026-09-18
- Policy expert: OpenAI exec's funding of Leading the Future still deters AI legislators — EthanJPerez · 2026-09-18
- 90-minute interview captures Sequoia legend Michael Moritz; Jim Goetz recalls being mentored by him — GuptaRK22 · 2026-09-18
- First-ever PyTorch Day Japan lands in Tokyo on December 10, CFP open till Sept 27 — PyTorch · 2026-09-18
- NumPy creator Travis Oliphant on funding open source foundations in the AI era — teoliphant · 2026-09-18