Claude 4.5 Sonnet (Reasoning) vs GPT-5.4 nano (xhigh)

Anthropic · OpenAI · catalog 2026-09-14

GPT-5.4 nano (xhigh) beats Claude 4.5 Sonnet (Reasoning): cheaper ($0.179 vs $2.31/M) and at least as smart (index 21.2 vs 21.2).

	Claude 4.5 Sonnet (Reasoning)	GPT-5.4 nano (xhigh)
Speed (tok/s)	41.7 measured	154.2 measured
Blended $/M	$2.31 derived	$0.179 derived
Intelligence index	21.2 measured	21.2 measured
TTFT (ms)	1489 measured	6427 measured
Context	—	400k list
Coding index	52 measured	56 measured
Agentic index	18 measured	18 measured

Claude 4.5 Sonnet (Reasoning) card · GPT-5.4 nano (xhigh) card · 3D observatory

Verdicts use price×intelligence dominance only, and only where both sides are measured; null cells stay null with their provenance (em-dash = not in catalog). Percentile-free by design — this page compares two models, not the field. Generated page — do not hand-edit.