Gemma 4 12B (Reasoning)

Google

ReasoningVision ModelApache 2.0

Analysis of Google's Gemma 4 12B (Reasoning) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.

Context

Release Date: Jun 03, 2026
Window: 256k

PricingPer 1M tokens

Input: $0.1
Output: $0.3
Blended 3:1: $0.15

Capabilities

Speed: 125 t/s
Input
Output
Reasoning tokens

Latency

TTFT: 2.38 ms
500 token response: 22.46 s

Benchmarks

Reasoning: ●○○○○
Coding: ●○○○○
GPQA: 75.3%
HLE: 14.8%
SciCode: 38.2%

Analysis of Google's Gemma 4 12B (Reasoning) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.