Model Comparator

Compare up to four models using the same criteria.

Granite 4.2 3B
IBM
Mistral Medium 3.1
Mistral

Differences only

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

Model Comparator
Metrics	Granite 4.2 3B IBM	Mistral Medium 3.1 Mistral
Intelligence	9.1	Best: 9.2
Coding	17.5	Best: 20.5
Math	—	38.3
Agentic	0.9	Best: 1.9
Speed	Best: 223 t/s	149 t/s
TTFT	Best: 0.5 s	2.23 s
Input · $ / 1M tokens	Best: $0.030	$0.40×13.3 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $0.12	$2×16.7 relative to the lowest price among the compared models
Context window	Best: 131K	128K
Reasoning	Yes	No
Open weights	Yes	No
Cost / task	$0.0060	—

Intelligence

Granite 4.2 3B: 9.1
Mistral Medium 3.1: Best: 9.2

Coding

Granite 4.2 3B: 17.5
Mistral Medium 3.1: Best: 20.5

Math

Granite 4.2 3B: —
Mistral Medium 3.1: 38.3

Agentic

Granite 4.2 3B: 0.9
Mistral Medium 3.1: Best: 1.9

Speed

Granite 4.2 3B: Best: 223 t/s
Mistral Medium 3.1: 149 t/s

TTFT

Granite 4.2 3B: Best: 0.5 s
Mistral Medium 3.1: 2.23 s

Input · $ / 1M tokens

Granite 4.2 3B: Best: $0.030
Mistral Medium 3.1: $0.40×13.3 relative to the lowest price among the compared models

Output · $ / 1M tokens

Granite 4.2 3B: Best: $0.12
Mistral Medium 3.1: $2×16.7 relative to the lowest price among the compared models

Context window

Granite 4.2 3B: Best: 131K
Mistral Medium 3.1: 128K

Reasoning

Granite 4.2 3B: Yes
Mistral Medium 3.1: No

Open weights

Granite 4.2 3B: Yes
Mistral Medium 3.1: No

Cost / task

Granite 4.2 3B: $0.0060
Mistral Medium 3.1: —

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 3B9.1 · $14.91
Mistral Medium 3.19.2 · $405.87