Model Comparator

Compare up to four models using the same criteria.

Mistral Small 4 (Reasoning)
Mistral
Gemma 3 1B Instruct
Google

Differences only

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

Model Comparator
Metrics	Mistral Small 4 (Reasoning) Mistral	Gemma 3 1B Instruct Google
Intelligence	4.3	Best: 4.8
Coding	26.6	—
Math	—	3.3
Agentic	0.8	—
Speed	166 t/s	—
TTFT	0.92 s	—
Input · $ / 1M tokens	$0.15	—
Output · $ / 1M tokens	$0.60	—
Context window	256K	Best: 1M
Reasoning	Yes	No
Open weights	Yes	Yes
Cost / task	$0.0399	—

Intelligence

Mistral Small 4 (Reasoning): 4.3
Gemma 3 1B Instruct: Best: 4.8

Coding

Mistral Small 4 (Reasoning): 26.6
Gemma 3 1B Instruct: —

Math

Mistral Small 4 (Reasoning): —
Gemma 3 1B Instruct: 3.3

Agentic

Mistral Small 4 (Reasoning): 0.8
Gemma 3 1B Instruct: —

Speed

Mistral Small 4 (Reasoning): 166 t/s
Gemma 3 1B Instruct: —

TTFT

Mistral Small 4 (Reasoning): 0.92 s
Gemma 3 1B Instruct: —

Input · $ / 1M tokens

Mistral Small 4 (Reasoning): $0.15
Gemma 3 1B Instruct: —

Output · $ / 1M tokens

Mistral Small 4 (Reasoning): $0.60
Gemma 3 1B Instruct: —

Context window

Mistral Small 4 (Reasoning): 256K
Gemma 3 1B Instruct: Best: 1M

Reasoning

Mistral Small 4 (Reasoning): Yes
Gemma 3 1B Instruct: No

Open weights

Mistral Small 4 (Reasoning): Yes
Gemma 3 1B Instruct: Yes

Cost / task

Mistral Small 4 (Reasoning): $0.0399
Gemma 3 1B Instruct: —

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 4 (Reasoning)4.3 · $0.0399

Not plotted for lack of data on these axes: Gemma 3 1B Instruct.