Model Comparator

Compare up to four models using the same criteria.

Mistral Large 3 2512
Mistral
Llama 4 Maverick
Meta

Differences only

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

Model Comparator
Metrics	Mistral Large 3 2512 Mistral	Llama 4 Maverick Meta
Intelligence	9.3	9.3
Coding	Best: 20.1	16.3
Math	—	19.3
Agentic	Best: 1	0.6
Speed	—	57.7 t/s
TTFT	—	1.12 s
Input · $ / 1M tokens	$0.50×2 relative to the lowest price among the compared models	Best: $0.25
Output · $ / 1M tokens	$1.50×1.7 relative to the lowest price among the compared models	Best: $0.87
Context window	262K	Best: 1M
Reasoning	No	No
Open weights	Yes	Yes
Cost / task	—	$0.0382

Intelligence

Mistral Large 3 2512: 9.3
Llama 4 Maverick: 9.3

Coding

Mistral Large 3 2512: Best: 20.1
Llama 4 Maverick: 16.3

Math

Mistral Large 3 2512: —
Llama 4 Maverick: 19.3

Agentic

Mistral Large 3 2512: Best: 1
Llama 4 Maverick: 0.6

Speed

Mistral Large 3 2512: —
Llama 4 Maverick: 57.7 t/s

TTFT

Mistral Large 3 2512: —
Llama 4 Maverick: 1.12 s

Input · $ / 1M tokens

Mistral Large 3 2512: $0.50×2 relative to the lowest price among the compared models
Llama 4 Maverick: Best: $0.25

Output · $ / 1M tokens

Mistral Large 3 2512: $1.50×1.7 relative to the lowest price among the compared models
Llama 4 Maverick: Best: $0.87

Context window

Mistral Large 3 2512: 262K
Llama 4 Maverick: Best: 1M

Reasoning

Mistral Large 3 2512: No
Llama 4 Maverick: No

Open weights

Mistral Large 3 2512: Yes
Llama 4 Maverick: Yes

Cost / task

Mistral Large 3 2512: —
Llama 4 Maverick: $0.0382

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 3 25129.3 · $0.75
Llama 4 Maverick9.3 · $0.405