Query a 9B index with the 0.6B model: half the accuracy gap at zero query-time cost
antoine_chaffin · x · 2026-10-08
The shared embedding space enables cross-model retrieval. Evaluating the 0.6B model querying a 9B index versus symmetric 9B and 0.6B setups: querying the 9B index with the smaller model boosts scores over the 0.6B index at no query-time cost. The 9B for querying is still stronger, but the 0.6B closes roughly half the gap.
Related event: Perplexity Open-Sources Multimodal Embedding Models pplx-embed-v2-late(38 posts)→
More from Models
- ChatGPT Work mode vs Codex: same quota, far more tasks done per 5-hour window — sasik520 · 2026-10-08
- Epoch's InnovationEval: AI agents still far from producing real research innovations — Afinetheorem · 2026-10-08
- 113 decision models in 3 weeks: 70 built on Qwen, sub-cent per call — jonathanmalkin · 2026-10-08
- User reports Haiku 5.5 is a major workflow upgrade in screenshot post — Sorcerer12345 · 2026-10-08
- OpenRouter launches Decision Model Rankings, with typesafeai leading all categories — gaganghotra_ · 2026-10-08
- OpenAI launches Intelligent UI: ChatGPT now answers with fully interactive interfaces — gdb · 2026-10-08