Model Comparator

Compare up to four models using the same criteria.

Grok 4.20 0309 (Non-reasoning)
SpaceXSI
Gemma 4 31B (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 (Non-reasoning) SpaceXSI	Gemma 4 31B (Reasoning) Google
Intelligence	14.6	Best: 14.7
Coding	—	43.4
Agentic	—	4.2
Speed	—	35.5 t/s
TTFT	—	1.08 s
Input · $ / 1M tokens	$2	—
Output · $ / 1M tokens	$6	—
Context window	Best: 2M	256K
Reasoning	No	Yes
Open weights	No	Yes
Cost / task	—	$0

Intelligence

Grok 4.20 0309 (Non-reasoning): 14.6
Gemma 4 31B (Reasoning): Best: 14.7

Coding

Grok 4.20 0309 (Non-reasoning): —
Gemma 4 31B (Reasoning): 43.4

Agentic

Grok 4.20 0309 (Non-reasoning): —
Gemma 4 31B (Reasoning): 4.2

Speed

Grok 4.20 0309 (Non-reasoning): —
Gemma 4 31B (Reasoning): 35.5 t/s

TTFT

Grok 4.20 0309 (Non-reasoning): —
Gemma 4 31B (Reasoning): 1.08 s

Input · $ / 1M tokens

Grok 4.20 0309 (Non-reasoning): $2
Gemma 4 31B (Reasoning): —

Output · $ / 1M tokens

Grok 4.20 0309 (Non-reasoning): $6
Gemma 4 31B (Reasoning): —

Context window

Grok 4.20 0309 (Non-reasoning): Best: 2M
Gemma 4 31B (Reasoning): 256K

Reasoning

Grok 4.20 0309 (Non-reasoning): No
Gemma 4 31B (Reasoning): Yes

Open weights

Grok 4.20 0309 (Non-reasoning): No
Gemma 4 31B (Reasoning): Yes

Cost / task

Grok 4.20 0309 (Non-reasoning): —
Gemma 4 31B (Reasoning): $0

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 · $0

Not plotted for lack of data on these axes: Grok 4.20 0309 (Non-reasoning).