The Embedder's Dilemma: LLMs Are Better, but at What Cost?

A new study comparing ten LLMs and 26 embedding models across 37 tasks finds the best LLM (Gemini 3.1 Pro, 77.6) and the best embedding model (77.2) are effectively tied, but LLMs cost up to 1,431x more (USD 154 vs. USD 0.11 per benchmark pass) and process tokens 2.5 to 736x slower. The authors recommend using embedding models for similarity, classification, and clustering, and reserving LLMs for reasoning-intensive retrieval.

Computer Science Computation and Language Submitted on 13 Aug 2026 Title:The Embedder's Dilemma: LLMs Are Better, but at What Cost? View PDF /pdf/2608.12875 HTML experimental https://arxiv.org/html/2608.12875v1 Abstract:Should you replace your text-embedding pipeline with a large language model? We answer this with a controlled, cost-aware comparison of ten LLMs across six families and 26 embedding models 118M to 14B parameters on 37 tasks spanning classification, semantic textual similarity STS , clustering, pair classification, and retrieval. In aggregate the two paradigms are effectively tied: the best LLM Gemini 3.1 Pro, 77.6 and the best embedding model 77.2 differ by 0.4 points. Their strengths differ by task: LLMs lead on reasoning-heavy retrieval, embedding models lead on classification, and the two match on clustering, STS, and pair classification. Reaching that parity is expensive. An LLM costs up to 1,431x more than an embedding model of comparable quality USD 154 vs. USD 0.11 per benchmark pass , and the open LLMs tested process tokens 2.5 to 736x more slowly on the same GPU. Reasoning tokens account for 28 to 81% of LLM inference cost; lower reasoning budgets preserve or improve retrieval quality for most models in our ablation. The Pareto frontier contains the leading embedding models and one LLM, Gemini 3.1 Pro. These results support a division of labour: use embedding models for similarity, classification, and clustering, and reserve LLMs for reasoning-intensive retrieval. Our code, datasets, and results are publicly available at this https URL . References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .