Model Releases
Qdrant Builds a 10-Billion-Document Vector Search Benchmark Dataset on Vultr
Qdrant has released **Qdrant‑Fineweb‑10B**, a public benchmark dataset comprising dense and sparse embeddings for 10 billion documents from the FineWeb corpus and exact results for 120,000 queries to
Qdrant has released Qdrant‑Fineweb‑10B, a public benchmark dataset comprising dense and sparse embeddings for 10 billion documents from the FineWeb corpus and exact results for 120,000 queries to depth 1,000. The dataset was generated on Vultr’s cloud infrastructure in roughly five days using Alibaba’s gte‑multilingual‑base model, enabling developers to evaluate vector search accuracy, indexing speed, sharding, and memory usage at realistic production scale.
Related
- VIBE: Vector Index Benchmark for Embeddings
- Hybrid privacy-aware semantic search: SVD-truncated document geometry and CKKS-encrypted query reranking under a restricted threat model
- SHARD: cell-keyed residual splitting for alignment-resistant private dense retrieval
- REIGN: Refurbished Embeddings with Integrated Guidance Networks for Efficient Context-Length Scaling
Source: Vultr | 2026-09-01