Perplexity: Mixed-Model Agent Teams Score Higher and Cost Less

perplexity_ai · x · 2026-11-18

Perplexity shares results on mixed-model agent teams: on Terminal-Bench 4.1 and WANDR, every mixed team beat four copies of its lead model, gaining +0.008 to +0.125 and +0.015 to +0.064 respectively.

Costs favor teams too — the best mixed teams cost $10.31 and $54.50 per run versus $13 and $66.41 for four lead-model copies. On WANDR, three of four teams also finished sooner than the model working alone: teams are faster, better, and cheaper.

Related event: Perplexity Finds Mixed-Model Agent Teams Beat Identical Model Copies(4 posts)→

Original post →

More from coding & agent

coding & agent channel →