GPT-5.6 Terra Tops LLM Listwise Reranking; Luna Is 10x Cheaper for Near-Parity

CShorten30 · x · 2026-11-16

Part 5 of the thread adds an LLM listwise reranking stage over zerank-2's top-20 (from hybrid retrieval at k=2,000), testing three OpenAI models with the same prompt, reasoning effort set to none, averaged over 3 trials:

Related event: Reranking Study Finds Two-Stage Pipeline Beats Fusion and Deeper Windows(13 posts)→

Original post →

More from Research

Research channel →