---
id: "quote-two-beats-sixteen"
type: "quote"
source_timestamps: ["¶4"]
tags: ["performance", "efficiency"]
related: ["claim-two-diverse-beats-sixteen", "entity-mark-purdy"]
speaker: "Mark Purdy"
speakers: ["Mark Purdy"]
quote: "match or exceed the performance of 16 homogeneous agents."
sources: ["agentic"]
sourceVaultSlug: "hbr-seg-agentic"
originDay: 6
articleStem: "hbr-new-28-agent-teams-different-models"
sourceUrl: "https://hbr.org/2026/06/the-strongest-teams-of-ai-agents-will-be-built-using-different-models"
sourceTitle: "The Strongest Teams of AI Agents Will Be Built Using Different Models"
---
# Two diverse agents match sixteen homogeneous ones

> Another study showed that just two diverse agents can "**match or exceed the performance of 16 homogeneous agents.**"

— [[entity-mark-purdy]] (author), citing a study

The most compressed statement of the article's efficiency argument, underpinning [[claim-two-diverse-beats-sixteen]]: diversity, not sheer agent count, is the multiplier. See the enrichment caveat on that claim — the figure is best read as an illustrative case-study result rather than a generalizable benchmark.