Model Comparator

Compare up to four models using the same criteria.

Differences only

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

Model Comparator
Metrics	Ministral 3 8B 2512 (batch) Mistral	Granite 4.2 30B IBM
Intelligence	5.5	5.5
Coding	9.7	Best: 29.9
Agentic	0.6	Best: 3.5
Speed	—	41.4 t/s
TTFT	—	0.97 s
Input · $ / 1M tokens	Best: $0.075	$0.16×2.1 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $0.075	$0.65×8.7 relative to the lowest price among the compared models
Context window	Best: 262K	131K
Reasoning	—	Yes
Open weights	Yes	Yes
Cost / task	—	$0.0717

Intelligence

Ministral 3 8B 2512 (batch): 5.5
Granite 4.2 30B: 5.5

Coding

Ministral 3 8B 2512 (batch): 9.7
Granite 4.2 30B: Best: 29.9

Agentic

Ministral 3 8B 2512 (batch): 0.6
Granite 4.2 30B: Best: 3.5

Speed

Ministral 3 8B 2512 (batch): —
Granite 4.2 30B: 41.4 t/s

TTFT

Ministral 3 8B 2512 (batch): —
Granite 4.2 30B: 0.97 s

Input · $ / 1M tokens

Ministral 3 8B 2512 (batch): Best: $0.075
Granite 4.2 30B: $0.16×2.1 relative to the lowest price among the compared models

Output · $ / 1M tokens

Ministral 3 8B 2512 (batch): Best: $0.075
Granite 4.2 30B: $0.65×8.7 relative to the lowest price among the compared models

Context window

Ministral 3 8B 2512 (batch): Best: 262K
Granite 4.2 30B: 131K

Reasoning

Ministral 3 8B 2512 (batch): —
Granite 4.2 30B: Yes

Open weights

Ministral 3 8B 2512 (batch): Yes
Granite 4.2 30B: Yes

Cost / task

Ministral 3 8B 2512 (batch): —
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.

Ministral 3 8B 2512 (batch)5.5 · $0.075
Granite 4.2 30B5.5 · $0.282