Artificial Analysis' Intelligence Index: Sonnet 5.5 (max) ranks above GPT-6 Astra (max) and behind only Opus 5.5 (max) but has the highest token use of them all (Artificial Analysis)

Artificial Analysis’ latest ranking shows Sonnet 5.5 (max) jumping 18 points to #2 on the Intelligence Index, ahead of GPT-6 Astra (max) and just behind Opus 5.5 (max). For CIOs, the key implication is that top-tier model capability is now increasingly tied to heavier token consumption, which can drive up inference costs and latency; IT teams should treat model selection as a cost-performance tradeoff, not just a quality decision.