Perplexity's 0.6B embedding model scores 62.3 on ViDoRe v3, beating larger rivals
antoine_chaffin · x · 2026-10-08
Perplexity's team shared results on the ViDoRe v3 multimodal retrieval benchmark: their 9B model averages 65.2%, outperforming nemotron-colembed-v2-8b and only trailing the vision-specific EVIE at a much larger embedding dimension. The smaller 0.6B model hits 62.3%, beating nemotron-colembed-v2-4b and qwen3-vl-embed-8b, and matching topk's 2B model — remarkably competitive for its size.
Related event: Perplexity Open-Sources Multimodal Embedding Models pplx-embed-v2-late(38 posts)→
More from Models
- ChatGPT on Browser Shows 'Capabilities Reduced' Warning — A New Kind of Rate Limit? — jasondeanlee · 2026-10-08
- 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