Model Comparator

Compare up to four models using the same criteria.

Mistral Large 3
Mistral
Mistral Large 3 2512
Mistral

Differences only

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

Model Comparator
Metrics	Mistral Large 3 Mistral	Mistral Large 3 2512 Mistral
Intelligence	9.3	9.3
Coding	20.1	20.1
Math	38	—
Agentic	1	1
Speed	76.1 t/s	—
TTFT	1.05 s	—
Input · $ / 1M tokens	$0.50	$0.50
Output · $ / 1M tokens	$1.50	$1.50
Context window	256K	Best: 262K
Reasoning	No	No
Open weights	Yes	Yes
Cost / task	$0.0311	—

Intelligence

Mistral Large 3: 9.3
Mistral Large 3 2512: 9.3

Coding

Mistral Large 3: 20.1
Mistral Large 3 2512: 20.1

Math

Mistral Large 3: 38
Mistral Large 3 2512: —

Agentic

Mistral Large 3: 1
Mistral Large 3 2512: 1

Speed

Mistral Large 3: 76.1 t/s
Mistral Large 3 2512: —

TTFT

Mistral Large 3: 1.05 s
Mistral Large 3 2512: —

Input · $ / 1M tokens

Mistral Large 3: $0.50
Mistral Large 3 2512: $0.50

Output · $ / 1M tokens

Mistral Large 3: $1.50
Mistral Large 3 2512: $1.50

Context window

Mistral Large 3: 256K
Mistral Large 3 2512: Best: 262K

Reasoning

Mistral Large 3: No
Mistral Large 3 2512: No

Open weights

Mistral Large 3: Yes
Mistral Large 3 2512: Yes

Cost / task

Mistral Large 3: $0.0311
Mistral Large 3 2512: —

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 Large 39.3 · $0.75
Mistral Large 3 25129.3 · $0.75