⚖️Purpose-built rerankers such as rerank-2.5 >>> LLMs
- Up to 60x cheaper & 48x faster than SOTA LLMs
- Beat LLM rerankers by up to 15% in accuracy (NDCG@10)
- Strong first-stage retrieval + specialized reranker = best reranking quality
❌ Long context windows don't help LLM rerankers. Single-pass reranking significantly underperforms sliding window reranking, undermining the value of longer context windows for reranking.
💰rerank-2.5 costs $0.05 per 1M tokens vs. $1.25-$3 for LLMs such as Gemini 2.5 Pro, GPT-5, and Claude Sonnet 4.5.
⚡rerank-2.5 offers the best reranking performance, while being 9x, 36x, and 48x faster than Claude Sonnet 4.5, GPT-5, and Gemini 2.5 Pro, respectively.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
reranking — A second pass that re-scores retrieved candidates by reading each one against the query, fixing the ordering that fast vector search got approximately right.
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
Why it matters
If you rerank with a frontier LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition →, this puts numbers on the cost and latency you pay, and reports that a long context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → does not remove the need for sliding window passes.
Read the full thread on X ↗
