PageIndex

@PageIndexAI

The document retrieval layer for AI

London

pageindex.ai

Joined June 2023

308 Following

1,914 Followers

Replies Reposts Media Articles

PageIndex
@PageIndexAI
3h
Congratulations to @OpenAI on the launch of GPT-6.1 Terra! 🚀 Amazing performance! GPT-6.1 Terra joins the accuracy–cost frontier in our PageIndex Financial QA Benchmark. At max reasoning, it hits 96.3% accuracy, just 2.4 percentage points behind Claude Opus 5.5 (max), at about
4
PageIndex
@PageIndexAI
Oct 24
Congratulations to @Kimi_Moonshot on Kimi K3.1 Pro! How does it perform with PageIndex? In our Financial QA Benchmark, it outperforms GPT-6.1 Sol in accuracy! 🚀 Try it for free on the PageIndex Playground: dash.pageindex.ai
5
PageIndex
@PageIndexAI
Oct 23
PageIndex is a vectorless RAG framework that uses LLMs for retrieval. Developers often ask: Which LLM works best with PageIndex? Today, we're launching the PageIndex Benchmark, starting with financial QA and comparing leading LLMs on accuracy and cost. Congratulations to
MiniMax (official) and Google Gemini
2
PageIndex
@PageIndexAI
Oct 22
Introducing PageIndex Playground🚀 PageIndex is a vectorless, reasoning-based RAG framework that uses LLMs, not embeddings, to retrieve information. Now you can try it with the latest AI models. Same document. Same question. Different models. Compare responses across models,
1
PageIndex
@PageIndexAI
Oct 21
Vectorless RAG can be both more accurate and cheaper than vector-based RAG. We compared PageIndex against a range of commonly used embedding models on financial documents. Accuracy and cost per 1K queries: • PageIndex: 100% at $110 • Best vector RAG (Voyage 4, top-100): 92%
PageIndex
@PageIndexAI
Oct 16
@GoogleDeepMind Gemini Embedding 2 is the SOTA embedding model for vector-based retrieval. We benchmarked PageIndex against vector-based retrieval powered by Gemini Embedding 2, comparing both accuracy and cost on financial reports. Run the benchmark: github.com/VectifyAI/Page…