Model Comparator

Compare up to four models using the same criteria.

Mistral Small (Feb '24)
Mistral
Granite 4.2 30B
IBM

Differences only

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

Model Comparator
Metrics	Mistral Small (Feb '24) Mistral	Granite 4.2 30B IBM
Intelligence	5.5	5.5
Coding	—	29.9
Agentic	—	3.5
Speed	Best: 157 t/s	41.4 t/s
TTFT	Best: 0.73 s	0.97 s
Input · $ / 1M tokens	Best: $0.15	$0.16×1.1 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $0.60	$0.65×1.1 relative to the lowest price among the compared models
Context window	33K	Best: 131K
Reasoning	No	Yes
Open weights	No	Yes
Cost / task	—	$0.0717

Intelligence

Mistral Small (Feb '24): 5.5
Granite 4.2 30B: 5.5

Coding

Mistral Small (Feb '24): —
Granite 4.2 30B: 29.9

Agentic

Mistral Small (Feb '24): —
Granite 4.2 30B: 3.5

Speed

Mistral Small (Feb '24): Best: 157 t/s
Granite 4.2 30B: 41.4 t/s

TTFT

Mistral Small (Feb '24): Best: 0.73 s
Granite 4.2 30B: 0.97 s

Input · $ / 1M tokens

Mistral Small (Feb '24): Best: $0.15
Granite 4.2 30B: $0.16×1.1 relative to the lowest price among the compared models

Output · $ / 1M tokens

Mistral Small (Feb '24): Best: $0.60
Granite 4.2 30B: $0.65×1.1 relative to the lowest price among the compared models

Context window

Mistral Small (Feb '24): 33K
Granite 4.2 30B: Best: 131K

Reasoning

Mistral Small (Feb '24): No
Granite 4.2 30B: Yes

Open weights

Mistral Small (Feb '24): No
Granite 4.2 30B: Yes

Cost / task

Mistral Small (Feb '24): —
Granite 4.2 30B: $0.0717

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.

Mistral Small (Feb '24)5.5 · $0.262
Granite 4.2 30B5.5 · $0.282