Perplexity reports benchmark gains and lower costs across effort levels

AIPerplexity says its medium effort setting rose from 55% to 77% on BrowseComp and DSQA, with almost 90% lower costs. It reports xhigh held 76.5% on WANDR, its benchmark for long, multi-entity research, at 75% lower cost than August.

Perplexity DevelopersOfficial

@perplexitydevs

View on X

Part of a thread · earlier post

medium effort increased its score from 55% to 77% on BrowseComp and DSQA, with almost 90% lower costs.

xhigh maintained 76.5% on WANDR, Perplexity's benchmark for long, multi-entity research, with 75% lower costs versus August.

ultra holds the highest WANDR score at 85.9%.

Source details

Perplexity Developers · x.comPublished Nov 5, 6:17 PM ET

Original title: medium effort increased its score from 55% to 77% on BrowseComp and DSQA, with almost 90% lower costs.

Topics

Evals & benchmarks