Compare AI Models

Comparing the specifications and intelligence benchmarks for Claude Opus 4.5 (Reasoning), Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort).

Model	Intelligence	MMLU Pro	Context	GPQA	TTFT (s)	Speed (T/s)	Input Price (1M)	Output Price (1M)
Claude Opus 4.5 (Reasoning) Anthropic	49.7	89.5%	-	86.6%	12.23	64	$5.00	$25.00
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)New Anthropic	51.7	-	-	87.5%	35.35	64	$3.00	$15.00

Claude Opus 4.5 (Reasoning) vs Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) Comparison 2026: Pricing & Benchmarks