Stop paying for embedding dimensions above 768 — and default to hybrid retrieval

CodeSOTA·low signal

Current MTEB analysis puts Qwen3-Embedding-8B at 70.6, above OpenAI (64.6) and Google (68.3), reversing the closed-source lead for teams with GPU infrastructure. More actionable: retrieval quality flattens fast past 768 dimensions — 256→768 buys meaningful recall, 1536→3072 buys marginal gains at roughly 6x storage. Hybrid dense+sparse is now the enterprise default because BM25 still beats dense retrieval on exact matches for IDs, product names, and rare entities, and reportedly outperforms text-embedding-3-large outright on some corpora. Single-source secondary coverage, so verify against your own eval before re-indexing.