Model Comparator

Compare up to four models using the same criteria.

Gemma 4 12B (Non-reasoning)
Google
Gemini 2.0 Flash Thinking Experimental (Jan '25)
Google

Differences only

✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.

Model Comparator
Metrics	Gemma 4 12B (Non-reasoning) Google	Gemini 2.0 Flash Thinking Experimental (Jan '25) Google
Intelligence	9.4	9.4
Coding	—	24.1
Speed	111 t/s	—
TTFT	2.49 s	—
Input · $ / 1M tokens	$0.10	—
Output · $ / 1M tokens	$0.30	—
Context window	262K	Best: 1M
Reasoning	No	Yes
Open weights	Yes	No

Intelligence

Gemma 4 12B (Non-reasoning): 9.4
Gemini 2.0 Flash Thinking Experimental (Jan '25): 9.4

Coding

Gemma 4 12B (Non-reasoning): —
Gemini 2.0 Flash Thinking Experimental (Jan '25): 24.1

Speed

Gemma 4 12B (Non-reasoning): 111 t/s
Gemini 2.0 Flash Thinking Experimental (Jan '25): —

TTFT

Gemma 4 12B (Non-reasoning): 2.49 s
Gemini 2.0 Flash Thinking Experimental (Jan '25): —

Input · $ / 1M tokens

Gemma 4 12B (Non-reasoning): $0.10
Gemini 2.0 Flash Thinking Experimental (Jan '25): —

Output · $ / 1M tokens

Gemma 4 12B (Non-reasoning): $0.30
Gemini 2.0 Flash Thinking Experimental (Jan '25): —

Context window

Gemma 4 12B (Non-reasoning): 262K
Gemini 2.0 Flash Thinking Experimental (Jan '25): Best: 1M

Reasoning

Gemma 4 12B (Non-reasoning): No
Gemini 2.0 Flash Thinking Experimental (Jan '25): Yes

Open weights

Gemma 4 12B (Non-reasoning): Yes
Gemini 2.0 Flash Thinking Experimental (Jan '25): No

Each reasoning level remains a separate configuration.

Score and cost

Each line joins the reasoning levels of a compared model; the large point marks the configuration in the table. The top-right corner holds the best score for the lowest cost. Select another point to compare that level.

Gemma 4 12B (Non-reasoning)9.4 · $0.15

Not plotted for lack of data on these axes: Gemini 2.0 Flash Thinking Experimental (Jan '25).