What matters in AI.

Subscribe

Sonnet 5.5 costs 77% less for each task at the xhigh level than at max

The max level gets 68 points on the Coding Agent Index, and the xhigh level gets 63.

Claimed, not confirmed

Tests by Artificial Analysis show that Sonnet 5.5 from Anthropic has the top score on its Coding Agent Index. This is the result in Claude Code at the max level. The score is 68. At the xhigh level the score is 63, but the cost of each task is $3.33 and not $14.19. This is 77% less cost for 5.5 less Index points.

Sources

  1. @ArtificialAnlys: Sonnet 5.5 tops the Coding Agent Index at max effort, while xhigh offers an attractive cost-performance trade-off: 63 points versus 68 for less than a quarter of the cost In Claude Cx.com
AI MATTER · NEWS · AI MATTER · NEWS ·14 OCT2026

Posted

Tags

More in Agents

All Agents news