Claude Sonnet 4.6 (Non-reasoning, High Effort) vs Claude Sonnet 5 (Adaptive Reasoning, Low Effort)

Anthropic · Anthropic · catalog 2026-09-14

Claude Sonnet 5 (Adaptive Reasoning, Low Effort) beats Claude Sonnet 4.6 (Non-reasoning, High Effort): cheaper ($1.54 vs $2.31/M) and at least as smart (index 24.7 vs 24.7).
Claude Sonnet 4.6 (Non-reasoning, High Effort)Claude Sonnet 5 (Adaptive Reasoning, Low Effort)
Speed (tok/s)42 measured55.8 measured
Blended $/M$2.31 derived$1.54 derived
Intelligence index24.7 measured24.7 measured
TTFT (ms)175 measured106 measured
Context1000k list—
Coding indexnot measured for both
Agentic indexnot measured for both

Claude Sonnet 4.6 (Non-reasoning, High Effort) card · Claude Sonnet 5 (Adaptive Reasoning, Low Effort) 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.