Model Comparator

Compare up to four models using the same criteria.

Mistral Small 3.1
Mistral
Pixtral Large
Mistral

Differences only

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

Model Comparator
Metrics	Mistral Small 3.1 Mistral	Pixtral Large Mistral
Intelligence	7.1	7.1
Coding	26.3	—
Math	Best: 3.7	2.3
Agentic	1.2	—
Speed	29 t/s	—
TTFT	0.98 s	—
Input · $ / 1M tokens	$0.080	—
Output · $ / 1M tokens	$0.135	—
Context window	128K	128K
Reasoning	No	No
Open weights	Yes	Yes
Cost / task	$0.0255	—

Intelligence

Mistral Small 3.1: 7.1
Pixtral Large: 7.1

Coding

Mistral Small 3.1: 26.3
Pixtral Large: —

Math

Mistral Small 3.1: Best: 3.7
Pixtral Large: 2.3

Agentic

Mistral Small 3.1: 1.2
Pixtral Large: —

Speed

Mistral Small 3.1: 29 t/s
Pixtral Large: —

TTFT

Mistral Small 3.1: 0.98 s
Pixtral Large: —

Input · $ / 1M tokens

Mistral Small 3.1: $0.080
Pixtral Large: —

Output · $ / 1M tokens

Mistral Small 3.1: $0.135
Pixtral Large: —

Context window

Mistral Small 3.1: 128K
Pixtral Large: 128K

Reasoning

Mistral Small 3.1: No
Pixtral Large: No

Open weights

Mistral Small 3.1: Yes
Pixtral Large: Yes

Cost / task

Mistral Small 3.1: $0.0255
Pixtral Large: —

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 3.17.1 · $0.0255

Not plotted for lack of data on these axes: Pixtral Large.