alphaXiv(@askalphaxiv):"The Embedder's Dilemma: LLMs Are Better, but at What Cost?" LLMs now match the best embedding models overall, but at up to 1,431x the cost. Embeddings still win on classification and tie on similarity and clustering, while LLMs are better on reasoning-heavy retrieval. So a good decision maker they proposed is use embeddings by default, and spend LLM compute only where reasoning actually helps.

2026.08.20 22:20

"The Embedder's Dilemma: LLMs Are Better, but at What Cost?" LLMs now match the best embedding models overall, but at up to 1,431x the cost. Embeddings still win on classification and tie on similarity and clustering, while LLMs are better on reasoning-heavy retrieval. So a good decision maker they proposed is use embeddings by default, and spend LLM compute only where reasoning actually helps.