Claude Sonnet 5 (Adaptive Reasoning, Max Effort) vs GPT-5.5 (xhigh)

Anthropic · OpenAI · catalog 2026-09-14

Trade-off: Claude Sonnet 5 (Adaptive Reasoning, Max Effort) is cheaper ($1.54 vs $4.35/M); GPT-5.5 (xhigh) scores higher on intelligence (38.6 vs 38.4).

	Claude Sonnet 5 (Adaptive Reasoning, Max Effort)	GPT-5.5 (xhigh)
Speed (tok/s)	73 measured	79.7 measured
Blended $/M	$1.54 derived	$4.35 derived
Intelligence index	38.4 measured	38.6 measured
TTFT (ms)	18739 measured	411 measured
Context	1000k list	1050k list
Coding index	72 measured	75 measured
Agentic index	44 measured	37 measured

Claude Sonnet 5 (Adaptive Reasoning, Max Effort) card · GPT-5.5 (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.