GPT-5.6 Luna (Non-reasoning) vs o4-mini (high)

OpenAI · OpenAI · catalog 2026-09-14

GPT-5.6 Luna (Non-reasoning) beats o4-mini (high): cheaper ($0.174 vs $0.856/M) and at least as smart (index 16.8 vs 16.7).
GPT-5.6 Luna (Non-reasoning)o4-mini (high)
Speed (tok/s)104.3 measured135.6 measured
Blended $/M$0.174 derived$0.856 derived
Intelligence index16.8 measured16.7 measured
TTFT (ms)9 measured217 measured
Context—200k list
Coding indexnot measured for both
Agentic indexnot measured for both

GPT-5.6 Luna (Non-reasoning) card · o4-mini (high) 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.