Perplexity Open-Sources WANDR Research Benchmark
inductionheads · x · 2026-07-15
Perplexity has open-sourced its internal research capability evaluation benchmark, WANDR.
They state that WANDR is an internal benchmark used to measure deep and wide research capabilities, serving as a crucial component in building the research abilities of the Perplexity Computer. Arav Srinivas also mentioned that internal evaluations and benchmarks are critical to their cost and performance tracking.
Related event: Perplexity open-sources internal research benchmark WANDR(9 posts)→
More from Apps
- What's the Real Dollar Cost of Everyday AI Agent Tasks? — Automatic-Pay-4121 · 2026-07-22
- Rowboat launches as an open-source, local-first AI coworker with memory — ycombinator · 2026-07-22
- Gorgias says it has raised over $100M to launch AI Agent 3.0 for customer support — Scobleizer · 2026-07-22
- Illume launches a 24/7 personal health companion that blends wearables and lab data — ycombinator · 2026-07-22
- Tesla’s summer update lets Grok make calls, control climate, and play music — Polymarket · 2026-07-22
- OpenAI appears to open an “Advertise in ChatGPT” page — montecarl · 2026-07-22