FinRank releases 1,185 manually authored SEC-filing questions and 6,021 hard negatives; its best tested 7B embedder reaches only 44.8% Recall@10 under the curated retrieval task.
Why it matters: Financial answers can look numerically plausible while retrieving the wrong company, period, or passage, hiding a provenance failure.
Qwen released Apache-2.0 embedding and reranking models at 0.6B, 4B and 8B sizes. The series supports more than 100 languages, 32,000-token inputs, instruction-aware retrieval and configurable embedding dimensions for search and retrieval systems.
Why it matters: Open retrieval models let teams tune quality, latency, storage and deployment location without depending on a proprietary embedding API.