Perplexity Releases Q2D-Web: A Benchmark with 190M Documents and 70k Agent-Reformulated Queries
antoine_chaffin · x · 2026-09-10
Perplexity introduces Q2D-Web (Query2Doc-Web), a benchmark and public leaderboard for evaluating retrieval in agentic RAG systems. Unlike common setups that focus on nDCG@10, it targets Recall@1000, measuring how embedding models perform on large-scale web search.
The benchmark scales up the earlier Q2D benchmark (released alongside pplx-embed-v1) by 7x, featuring 70k agent-reformulated queries and a 190M-document web corpus. The team hopes it becomes the modern "MS MARCO".
Related event: Perplexity Releases Q2D-Web, First Open Benchmark for Agentic RAG Retrieval(8 posts)→
More from Research
- Salesforce releases EvoHarnessBench to test agents against evolving tool harnesses — Salesforce · 2026-09-10
- Cornell uses AlphaFold to uncover new class of cellular 'off switch' linked to cancer — Dr_Singularity · 2026-09-10
- AI-built app visualizes Rentosertib anti-aging drug mechanism in ~40 minutes — DeryaTR_ · 2026-09-10
- AlphaFold helps Cornell researchers discover hidden cellular 'off switch' linked to cancer — Dr_Singularity · 2026-09-10
- Anthropic, FutureBio and HackIterate team up for cross-domain hard science push in October — Thom_Wolf · 2026-09-10
- Tsinghua + Qwen paper: rebuilding agent workspaces beats imitating trajectories, lifts Terminal-Bench to 58.1% — rohanpaul_ai · 2026-09-10