{"slug": "openai-s-embeddings-fell-to-13th-of-15-i-m-ditching-them-for-a-free-model-that", "title": "OpenAI's Embeddings Fell to 13th of 15 — I'm Ditching Them for a Free Model That Wins by 11 Points", "summary": "OpenAI's text-embedding-3-large embedding model has fallen to 13th place out of 15 on the 2026 aggregate embedding leaderboard with a score of 58.96, while the free, Apache 2.0-licensed Qwen3-Embedding-8B leads at 70.58, beating it by 11.6 points. The author argues that teams neglect benchmarking their retrieval layer, which is critical for RAG systems, and recommends switching to the superior open-source model.", "body_md": "Member-only story\n\n# OpenAI's Embeddings Fell to 13th of 15 — I'm Ditching Them for a Free Model That Wins by 11 Points\n\nThe most widely deployed embedding model in production RAG systems — OpenAI’s text-embedding-3-large — now sits **13th out of 15** on the 2026 aggregate embedding leaderboard, with a score of 58.96. The model beating it by **11.6 points** is Qwen3-Embedding-8B at 70.58, it’s Apache 2.0, and it costs exactly nothing to run. Even the 0.6B variant — small enough to run on a MacBook without a discrete GPU — beats OpenAI’s flagship API by 5.4 points.\n\nLet that sink in. Teams agonize for weeks over GPT-5.6 vs Opus 4.8 vs Grok for the generation layer, then ship the same embedding endpoint they copy-pasted from a LangChain tutorial in early 2024. The retrieval layer decides what your LLM even gets to see — and for most production RAG systems, that layer is now a bottom-quartile model.\n\nI spent this week auditing the 2026 embedding landscape the same way I audited vector databases last week: third-party leaderboards, independent benchmarks, and pricing sheets — not vendor blog posts. Here’s what the numbers say, why OpenAI’s 2024-vintage models fell so far, and exactly when you should (and shouldn’t) switch.\n\n## The layer nobody benchmarks\n\nThere’s a strange asymmetry in how teams build RAG. The generation model gets evaluated obsessively — everyone knows their LLM’s SWE-bench score, its cost per million tokens, its context window. The embedding model gets chosen once, by…", "url": "https://wpnews.pro/news/openai-s-embeddings-fell-to-13th-of-15-i-m-ditching-them-for-a-free-model-that", "canonical_source": "https://pub.towardsai.net/openais-embeddings-fell-to-13th-of-15-i-m-ditching-them-for-a-free-model-that-wins-by-11-points-f3290a7ee4cc?source=rss----98111c9905da---4", "published_at": "2026-07-11 10:05:13+00:00", "updated_at": "2026-07-11 10:39:40.450651+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products", "ai-tools", "ai-research"], "entities": ["OpenAI", "Qwen3-Embedding-8B", "LangChain", "GPT-5.6", "Opus 4.8", "Grok"], "alternates": {"html": "https://wpnews.pro/news/openai-s-embeddings-fell-to-13th-of-15-i-m-ditching-them-for-a-free-model-that", "markdown": "https://wpnews.pro/news/openai-s-embeddings-fell-to-13th-of-15-i-m-ditching-them-for-a-free-model-that.md", "text": "https://wpnews.pro/news/openai-s-embeddings-fell-to-13th-of-15-i-m-ditching-them-for-a-free-model-that.txt", "jsonld": "https://wpnews.pro/news/openai-s-embeddings-fell-to-13th-of-15-i-m-ditching-them-for-a-free-model-that.jsonld"}}