Model Comparator

Compare up to four models using the same criteria.

Gemma 4 12B (Reasoning)
Google
K-EXAONE (Reasoning)
LG AI Research

Differences only

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

Model Comparator
Metrics	Gemma 4 12B (Reasoning) Google	K-EXAONE (Reasoning) LG AI Research
Intelligence	14.2	Best: 14.4
Coding	31	Best: 32.1
Math	—	90.3
Speed	112 t/s	—
TTFT	2.5 s	—
Input · $ / 1M tokens	$0.10	—
Output · $ / 1M tokens	$0.30	—
Context window	262K	Best: 2.02M
Reasoning	Yes	Yes
Open weights	Yes	Yes

Intelligence

Gemma 4 12B (Reasoning): 14.2
K-EXAONE (Reasoning): Best: 14.4

Coding

Gemma 4 12B (Reasoning): 31
K-EXAONE (Reasoning): Best: 32.1

Math

Gemma 4 12B (Reasoning): —
K-EXAONE (Reasoning): 90.3

Speed

Gemma 4 12B (Reasoning): 112 t/s
K-EXAONE (Reasoning): —

TTFT

Gemma 4 12B (Reasoning): 2.5 s
K-EXAONE (Reasoning): —

Input · $ / 1M tokens

Gemma 4 12B (Reasoning): $0.10
K-EXAONE (Reasoning): —

Output · $ / 1M tokens

Gemma 4 12B (Reasoning): $0.30
K-EXAONE (Reasoning): —

Context window

Gemma 4 12B (Reasoning): 262K
K-EXAONE (Reasoning): Best: 2.02M

Reasoning

Gemma 4 12B (Reasoning): Yes
K-EXAONE (Reasoning): Yes

Open weights

Gemma 4 12B (Reasoning): Yes
K-EXAONE (Reasoning): Yes

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 (Reasoning)14.2 · $0.15

Not plotted for lack of data on these axes: K-EXAONE (Reasoning).