cd /news/artificial-intelligence/openai-s-embeddings-fell-to-13th-of-… · home topics artificial-intelligence article
[ARTICLE · art-55401] src=pub.towardsai.net ↗ pub= topic=artificial-intelligence verified=true sentiment=↓ negative

OpenAI's Embeddings Fell to 13th of 15 — I'm Ditching Them for a Free Model That Wins by 11 Points

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.

read1 min views1 publishedJul 11, 2026
OpenAI's Embeddings Fell to 13th of 15 — I'm Ditching Them for a Free Model That Wins by 11 Points
Image: Pub (auto-discovered)

Member-only story

The 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.

Let 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. I 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.

The layer nobody benchmarks #

There’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…

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @openai 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/openai-s-embeddings-…] indexed:0 read:1min 2026-07-11 ·