Claude Sonnet 4.6 (Non-reasoning, Low Effort) vs GPT-5.5 (Non-reasoning)

Anthropic · OpenAI · catalog 2026-09-14

Claude Sonnet 4.6 (Non-reasoning, Low Effort) beats GPT-5.5 (Non-reasoning): cheaper ($2.31 vs $4.35/M) and at least as smart (index 23.3 vs 23.2).
Claude Sonnet 4.6 (Non-reasoning, Low Effort)GPT-5.5 (Non-reasoning)
Speed (tok/s)42.2 measured77.9 measured
Blended $/M$2.31 derived$4.35 derived
Intelligence index23.3 measured23.2 measured
TTFT (ms)229 measured99 measured
Context——
Coding indexnot measured for both
Agentic indexnot measured for both

Claude Sonnet 4.6 (Non-reasoning, Low Effort) card · GPT-5.5 (Non-reasoning) 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.