Perplexity AI Releases WANDR: An Open Benchmark Evaluating Research Agents That Must Search Wide And Deep – MarkTechPost

Perplexity AI has released WANDR, an open benchmark designed to evaluate research agents on their ability to conduct comprehensive searches across multiple sources. The benchmark assesses how effectively these agents can explore broad information landscapes while simultaneously investigating specific topics in depth. WANDR aims to establish standardized metrics for evaluating the performance of research-focused AI systems.

Read Full Article →