Cohere Rerank 5 Pro lifts PDF retrieval nDCG@10 from 66.8 to 73.2 in Qdrant tests
qdrant_engine · x · 2026-10-23
Qdrant benchmarked Cohere's newly released Embed 5 family and Rerank 5 Pro on visually rich PDF retrieval:
- Rerank 5 Pro raised nDCG@10 from 66.8 to 73.2 on the same corpora — a drop-in gain for existing OCR-based pipelines.
- Embed 5 Pro scored 65.8 nDCG@10 across five public ViDoRe v3 corpora, beating ColPali, ColQwen2.5, and Jina-v4; only ColEmbed-3B-v2 (67.5) scored higher among compared models.
- Caveat: Embed 5's training data is unpublished, so test set overlap is possible.
The companion post combines Embed 5 with Qdrant 1.20's asymmetric quantization and BM25 hybrid search (no sparse vectors needed) for scalable PDF retrieval. Embed 5 comes in Pro and Fast tiers, both multimodal (text+image), 100+ languages, sharing one embedding space.
Related event: Qdrant Tests Cohere Embed 5: One Vector Per Page Beats ColPali at 64 Bytes(4 posts)→
More from Infra
- 2-bit quantized DeepSeek 4.1 Flash tested locally: KDL degrades but still works — bakawolf123 · 2026-10-23
- Developers now deploying 1T-parameter models on their own infrastructure — dejavucoder · 2026-10-23
- Liquid AI launches RIPL inference engine generating full LLM responses in 30ms — JosephJacks_ · 2026-10-23
- Tech infra manias historically last 4-6 years — next year is AI's fifth — oran_ge · 2026-10-23
- Cambricon revenue doubles: $1.34B in first three quarters, net profit up 131% — teortaxesTex · 2026-10-23
- Which US State Will Rebrand as 'The Data Center State' and Build a Sovereign Wealth Fund? — matt_slotnick · 2026-10-23