Model Comparator

Compare up to four models using the same criteria.

GPT-4 Turbo
OpenAI
Mistral Small 3.2
Mistral

Differences only

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

Model Comparator
Metrics	GPT-4 Turbo OpenAI	Mistral Small 3.2 Mistral
Intelligence	7	7
Coding	Best: 21.5	12.5
Math	—	27
Agentic	—	1
Speed	32.2 t/s	Best: 36.5 t/s
TTFT	2.99 s	Best: 0.93 s
Input · $ / 1M tokens	$10×133 relative to the lowest price among the compared models	Best: $0.075
Output · $ / 1M tokens	$30×150 relative to the lowest price among the compared models	Best: $0.20
Context window	128K	128K
Reasoning	No	No
Open weights	No	Yes
Cost / task	—	$0.109

Intelligence

GPT-4 Turbo: 7
Mistral Small 3.2: 7

Coding

GPT-4 Turbo: Best: 21.5
Mistral Small 3.2: 12.5

Math

GPT-4 Turbo: —
Mistral Small 3.2: 27

Agentic

GPT-4 Turbo: —
Mistral Small 3.2: 1

Speed

GPT-4 Turbo: 32.2 t/s
Mistral Small 3.2: Best: 36.5 t/s

TTFT

GPT-4 Turbo: 2.99 s
Mistral Small 3.2: Best: 0.93 s

Input · $ / 1M tokens

GPT-4 Turbo: $10×133 relative to the lowest price among the compared models
Mistral Small 3.2: Best: $0.075

Output · $ / 1M tokens

GPT-4 Turbo: $30×150 relative to the lowest price among the compared models
Mistral Small 3.2: Best: $0.20

Context window

GPT-4 Turbo: 128K
Mistral Small 3.2: 128K

Reasoning

GPT-4 Turbo: No
Mistral Small 3.2: No

Open weights

GPT-4 Turbo: No
Mistral Small 3.2: Yes

Cost / task

GPT-4 Turbo: —
Mistral Small 3.2: $0.109

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.

GPT-4 Turbo7 · $15
Mistral Small 3.27 · $0.106