Computer Use Evals Benchmarks Deep Research

WANDR

Benchmark for deep and wide research

Perplexity's benchmark and dataset for evaluating deep, wide research work, comprising 500 tasks represented as hierarchical, independently verifiable source-backed records.

Recent stories

1 linked story

releasePRIMARY2026-07-14

Perplexity releases WANDR benchmark with 500 deep-research tasks

Perplexity released WANDR, its internal benchmark for deep and wide research in Computer. The dataset has 500 tasks, 170,495 source-backed records and production-derived use cases.