Gemma 4 12B (Reasoning) vs Grok 4.20 0309 v2 (Non-reasoning)

Google · SpaceXAI · catalog 2026-09-14

Gemma 4 12B (Reasoning) beats Grok 4.20 0309 v2 (Non-reasoning): cheaper ($0.12 vs $0.64/M) and at least as smart (index 14.2 vs 14.2).
Gemma 4 12B (Reasoning)Grok 4.20 0309 v2 (Non-reasoning)
Speed (tok/s)106.5 measured94.3 measured
Blended $/M$0.12 derived$0.64 derived
Intelligence index14.2 measured14.2 measured
TTFT (ms)235 measured62 measured
Context——
Coding indexnot measured for both
Agentic indexnot measured for both

Gemma 4 12B (Reasoning) card · Grok 4.20 0309 v2 (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.