RRF fusion of three LLM rerankers underperforms Terra alone at 15x the cost
CShorten30 · x · 2026-11-16
Tweet 13/17: fusion fails at the listwise stage too. Equal-weight RRF of Mini, Luna, and Terra lands at 0.471 nDCG@10 — below Terra alone (0.488) — at 15x Luna's price. The table shows single-model scores: Mini 0.424, Luna 0.470, Terra 0.488 with 0.502 Success@1.
Related event: Reranking Study Finds Two-Stage Pipeline Beats Fusion and Deeper Windows(13 posts)→
More from Research
- BeyondBinding challenge launches: AI-designed antibodies get wet-lab tested — QuanquanGu · 2026-11-17
- Singularity-Bench: Opus 5.5 with Claude Code beats human baselines on building AI systems — armand_ruiz · 2026-11-17
- Open Vision Banana: fully open recipe turns image generators into multi-task perception systems — NielsRogge · 2026-11-17
- WebArena-Pro debuts as largest browser-agent benchmark, top agents score 62.3% — xhluca · 2026-11-17
- NeurIPS 2026 paper: RL-trained skills transfer poorly to composed reasoning tasks — StanfordAILab · 2026-11-17
- OpenAI warns CoT monitorability will degrade as models scale, researchers push back — gleech · 2026-11-17