Claude 4.5 Haiku (Non-reasoning) vs Gemma 4 31B (Reasoning)

Anthropic · Google · catalog 2026-09-14

Gemma 4 31B (Reasoning) beats Claude 4.5 Haiku (Non-reasoning): cheaper ($0 vs $0.77/M) and at least as smart (index 15.4 vs 15.4).
Claude 4.5 Haiku (Non-reasoning)Gemma 4 31B (Reasoning)
Speed (tok/s)77.4 measured35.5 measured
Blended $/M$0.77 derived$0 derived
Intelligence index15.4 measured15.4 measured
TTFT (ms)72 measured111 measured
Context——
Coding indexnot measured for both
Agentic indexnot measured for both

Claude 4.5 Haiku (Non-reasoning) card · Gemma 4 31B (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.