Model Comparator

Compare up to four models using the same criteria.

Granite 4.2 8B
IBM
Grok 4 Fast (Non-reasoning)
SpaceXSI

Differences only

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

Model Comparator
Metrics	Granite 4.2 8B IBM	Grok 4 Fast (Non-reasoning) SpaceXSI
Intelligence	11.1	11.1
Coding	22.4	—
Math	—	41.3
Agentic	1.3	—
Speed	130 t/s	—
TTFT	0.65 s	—
Input · $ / 1M tokens	Best: $0.060	$0.20×3.3 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $0.25	$0.50×2 relative to the lowest price among the compared models
Context window	131K	Best: 2M
Reasoning	Yes	No
Open weights	Yes	No
Cost / task	$0.0236	—

Intelligence

Granite 4.2 8B: 11.1
Grok 4 Fast (Non-reasoning): 11.1

Coding

Granite 4.2 8B: 22.4
Grok 4 Fast (Non-reasoning): —

Math

Granite 4.2 8B: —
Grok 4 Fast (Non-reasoning): 41.3

Agentic

Granite 4.2 8B: 1.3
Grok 4 Fast (Non-reasoning): —

Speed

Granite 4.2 8B: 130 t/s
Grok 4 Fast (Non-reasoning): —

TTFT

Granite 4.2 8B: 0.65 s
Grok 4 Fast (Non-reasoning): —

Input · $ / 1M tokens

Granite 4.2 8B: Best: $0.060
Grok 4 Fast (Non-reasoning): $0.20×3.3 relative to the lowest price among the compared models

Output · $ / 1M tokens

Granite 4.2 8B: Best: $0.25
Grok 4 Fast (Non-reasoning): $0.50×2 relative to the lowest price among the compared models

Context window

Granite 4.2 8B: 131K
Grok 4 Fast (Non-reasoning): Best: 2M

Reasoning

Granite 4.2 8B: Yes
Grok 4 Fast (Non-reasoning): No

Open weights

Granite 4.2 8B: Yes
Grok 4 Fast (Non-reasoning): No

Cost / task

Granite 4.2 8B: $0.0236
Grok 4 Fast (Non-reasoning): —

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.

Granite 4.2 8B11.1 · $0.107
Grok 4 Fast (Non-reasoning)11.1 · $0.275