Gemma 4 12B

Google

Compare Gemma 4 12B Count tokens for Gemma 4 12B

Context

n/a

Max output

n/a

Serving providers

Cheapest input

n/a /1M

Benchmarks

independent evaluations · source: Artificial Analysis

Speed & latency

Output speed

111 t/s

tokens / second

Time to first token

2.32s

latency

Headline indices

Intelligence Index

22.2

of 100

Coding Index

31.0

of 100

Agentic Index

7.9

of 100

Individual benchmarks · click a row for effort variants

Benchmark

Best score

Effort

Cost / task

CritPt

default

—

EvalComputeProxy

1384.6

default

—

GDPval

644.7

default

—

GPQA Diamond

75%

default

—

Humanity's Last Exam

16%

default

—

IFBench

74%

default

—

Long-Context Reasoning

62%

default

—

MMMU-Pro

70%

default

—

Omniscience

-52.7

default

—

Omniscience Accuracy

0.2

default

—

Omniscience Non Hallucination

0.3

reasoning: false

—

SciCode

38%

default

—

TerminalBench Hard

18%

default

—

TerminalBench v2.1

27%

default

—

τ-bench Banking

default

—

τ²-bench

36%

default

—

Pricing by serving provider

availability

No public price yet. Not offered on-demand at any tracked provider.

Price history

input + output $/1M since we started tracking

Input Output

Price history is accruing. We record a point each day a price changes; the full backfill lands shortly.

Other Google models

compare pricing across the Google lineup

Gemma 3 27B$0.00/1M · 8 providers Gemma 4 31B$0.09/1M · 8 providers Gemini 2.5 Flash$0.15/1M · 8 providers Gemini 2.5 Pro$1.25/1M · 7 providers Gemma 3 12B$0.05/1M · 5 providers Gemma 4 26B A4B $0.07/1M · 5 providers Gemini 3.1 Flash Lite$0.25/1M · 5 providers Gemini 3.7 Flash$0.38/1M · 5 providers

Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI