{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreicsw3ru5imrlzvdbbo6u362wymszykgordhlgp4ibyjnglnz26ili",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3miisy56hxv32"
},
"path": "/t/why-are-similarity-scores-lower-with-text-embedding-3-small/1377685#post_6",
"publishedAt": "2026-04-02T07:20:32.000Z",
"site": "https://community.openai.com",
"textContent": "I hope you’re right—and I agree that from an infrastructure and cost‑efficiency point of view, `ada‑002` likely has a strong profile. I also anticipate that `ada‑002` will stick around until a genuinely better replacement is available.\nFor now, we’re sticking with `ada‑002` where performance matters most, though we may still need to plan a move to `3‑small`, since unexpected model availability changes are risky for production systems that rely on stable embeddings",
"title": "Why are similarity scores lower with text-embedding-3-small?"
}