pplx-embed-v2 agentic retrieval evals: 9B model hits 64.0% on BrowseComp-Plus
antoine_chaffin · x · 2026-10-08
Perplexity's team shared more pplx-embed-v2 eval results, focusing on agentic retrieval.
- Evaluated on BrowseComp-Plus (text-only) and MADQA (multimodal)
- On text, the 9B model achieves 64.0% accuracy, ahead of every other ColBERT and dense model, while issuing fewer searches than any model except their own 0.6B
- The 0.6B also beats every model outside the family
The author highlights agentic retrieval as a core strength of multi-vector models.
Related event: Perplexity Open-Sources Multimodal Embedding Models pplx-embed-v2-late(38 posts)→
More from Models
- 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
- OpenAI launches Intelligent UI: ChatGPT now answers with fully interactive interfaces — gdb · 2026-10-08