Model Comparator

Compare up to four models using the same criteria.

Grok 4.20 0309 v2 (Non-reasoning)
SpaceXSI
Gemma 4 12B (Reasoning)
Google

Differences only

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

Model Comparator
Metrics	Grok 4.20 0309 v2 (Non-reasoning) SpaceXSI	Gemma 4 12B (Reasoning) Google
Intelligence	14.2	14.2
Coding	—	31
Speed	111 t/s	Best: 112 t/s
TTFT	Best: 0.61 s	2.49 s
Input · $ / 1M tokens	$1.25×12.5 relative to the lowest price among the compared models	Best: $0.10
Output · $ / 1M tokens	$2.50×8.3 relative to the lowest price among the compared models	Best: $0.30
Context window	Best: 2M	262K
Reasoning	No	Yes
Open weights	No	Yes

Intelligence

Grok 4.20 0309 v2 (Non-reasoning): 14.2
Gemma 4 12B (Reasoning): 14.2

Coding

Grok 4.20 0309 v2 (Non-reasoning): —
Gemma 4 12B (Reasoning): 31

Speed

Grok 4.20 0309 v2 (Non-reasoning): 111 t/s
Gemma 4 12B (Reasoning): Best: 112 t/s

TTFT

Grok 4.20 0309 v2 (Non-reasoning): Best: 0.61 s
Gemma 4 12B (Reasoning): 2.49 s

Input · $ / 1M tokens

Grok 4.20 0309 v2 (Non-reasoning): $1.25×12.5 relative to the lowest price among the compared models
Gemma 4 12B (Reasoning): Best: $0.10

Output · $ / 1M tokens

Grok 4.20 0309 v2 (Non-reasoning): $2.50×8.3 relative to the lowest price among the compared models
Gemma 4 12B (Reasoning): Best: $0.30

Context window

Grok 4.20 0309 v2 (Non-reasoning): Best: 2M
Gemma 4 12B (Reasoning): 262K

Reasoning

Grok 4.20 0309 v2 (Non-reasoning): No
Gemma 4 12B (Reasoning): Yes

Open weights

Grok 4.20 0309 v2 (Non-reasoning): No
Gemma 4 12B (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.

Grok 4.20 0309 v2 (Non-reasoning)14.2 · $1.56
Gemma 4 12B (Reasoning)14.2 · $0.15