GPT-4 Turbo vs Mistral Small 3.2

OpenAI · Mistral · catalog 2026-09-14

Mistral Small 3.2 beats GPT-4 Turbo: cheaper ($0.12 vs $12/M) and at least as smart (index 7 vs 7).
GPT-4 TurboMistral Small 3.2
Speed (tok/s)31.1 measured149.1 measured
Blended $/M$12 derived$0.12 derived
Intelligence index7 measured7 measured
TTFT (ms)345 measured72 measured
Context128k list—
Coding index22 measured13 measured
Agentic indexnot measured for both

GPT-4 Turbo card · Mistral Small 3.2 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.