Gemini 3.5 Flash (high) vs GPT-5.3 Codex (xhigh)

Google · OpenAI · catalog 2026-09-14

Gemini 3.5 Flash (high) beats GPT-5.3 Codex (xhigh): cheaper ($1.305 vs $1.869/M) and at least as smart (index 33 vs 32.5).
Gemini 3.5 Flash (high)GPT-5.3 Codex (xhigh)
Speed (tok/s)211.9 measured127.2 measured
Blended $/M$1.305 derived$1.869 derived
Intelligence index33 measured32.5 measured
TTFT (ms)1361 measured505 measured
Context1049k list400k list
Coding indexnot measured for both
Agentic indexnot measured for both

Gemini 3.5 Flash (high) card · GPT-5.3 Codex (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.