Model Comparator

Compare up to four models using the same criteria.

Granite 4.0 H Small
IBM
Ministral 3 14B
Mistral

Differences only

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

Model Comparator
Metrics	Granite 4.0 H Small IBM	Ministral 3 14B Mistral
Intelligence	6	6
Coding	—	14.4
Math	13.7	Best: 30
Agentic	—	1.1
Speed	14.4 t/s	Best: 67.9 t/s
TTFT	35.5 s	Best: 1.09 s
Input · $ / 1M tokens	Best: $0.060	$0.20×3.3 relative to the lowest price among the compared models
Output · $ / 1M tokens	$0.25×1.3 relative to the lowest price among the compared models	Best: $0.20
Context window	128K	Best: 256K
Reasoning	No	No
Open weights	Yes	Yes
Cost / task	—	$0.0194

Intelligence

Granite 4.0 H Small: 6
Ministral 3 14B: 6

Coding

Granite 4.0 H Small: —
Ministral 3 14B: 14.4

Math

Granite 4.0 H Small: 13.7
Ministral 3 14B: Best: 30

Agentic

Granite 4.0 H Small: —
Ministral 3 14B: 1.1

Speed

Granite 4.0 H Small: 14.4 t/s
Ministral 3 14B: Best: 67.9 t/s

TTFT

Granite 4.0 H Small: 35.5 s
Ministral 3 14B: Best: 1.09 s

Input · $ / 1M tokens

Granite 4.0 H Small: Best: $0.060
Ministral 3 14B: $0.20×3.3 relative to the lowest price among the compared models

Output · $ / 1M tokens

Granite 4.0 H Small: $0.25×1.3 relative to the lowest price among the compared models
Ministral 3 14B: Best: $0.20

Context window

Granite 4.0 H Small: 128K
Ministral 3 14B: Best: 256K

Reasoning

Granite 4.0 H Small: No
Ministral 3 14B: No

Open weights

Granite 4.0 H Small: Yes
Ministral 3 14B: Yes

Cost / task

Granite 4.0 H Small: —
Ministral 3 14B: $0.0194

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 4.0 H Small6 · $0.107
Ministral 3 14B6 · $0.20