Model Comparator

Compare up to four models using the same criteria.

Gemma 4 31B (Reasoning)
Google
Grok 3 mini Reasoning (High)
SpaceXSI

Differences only

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

Model Comparator
Metrics	Gemma 4 31B (Reasoning) Google	Grok 3 mini Reasoning (High) SpaceXSI
Intelligence	Best: 14.7	14.6
Coding	43.4	—
Math	—	84.7
Agentic	4.2	—
Speed	35.5 t/s	Best: 65.3 t/s
TTFT	Best: 1.08 s	1.74 s
Input · $ / 1M tokens	—	$0.30
Output · $ / 1M tokens	—	$0.50
Context window	256K	Best: 1M
Reasoning	Yes	Yes
Open weights	Yes	No
Cost / task	$0	—

Intelligence

Gemma 4 31B (Reasoning): Best: 14.7
Grok 3 mini Reasoning (High): 14.6

Coding

Gemma 4 31B (Reasoning): 43.4
Grok 3 mini Reasoning (High): —

Math

Gemma 4 31B (Reasoning): —
Grok 3 mini Reasoning (High): 84.7

Agentic

Gemma 4 31B (Reasoning): 4.2
Grok 3 mini Reasoning (High): —

Speed

Gemma 4 31B (Reasoning): 35.5 t/s
Grok 3 mini Reasoning (High): Best: 65.3 t/s

TTFT

Gemma 4 31B (Reasoning): Best: 1.08 s
Grok 3 mini Reasoning (High): 1.74 s

Input · $ / 1M tokens

Gemma 4 31B (Reasoning): —
Grok 3 mini Reasoning (High): $0.30

Output · $ / 1M tokens

Gemma 4 31B (Reasoning): —
Grok 3 mini Reasoning (High): $0.50

Context window

Gemma 4 31B (Reasoning): 256K
Grok 3 mini Reasoning (High): Best: 1M

Reasoning

Gemma 4 31B (Reasoning): Yes
Grok 3 mini Reasoning (High): Yes

Open weights

Gemma 4 31B (Reasoning): Yes
Grok 3 mini Reasoning (High): No

Cost / task

Gemma 4 31B (Reasoning): $0
Grok 3 mini Reasoning (High): —

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 31B (Reasoning)14.7 · 35.5 t/s
Grok 3 mini Reasoning (High)14.6 · 65.3 t/s