Model Comparator

Compare up to four models using the same criteria.

Gemma 4 12B (Reasoning)
Google
Mistral Medium 3.5
Mistral

Differences only

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

Model Comparator
Metrics	Gemma 4 12B (Reasoning) Google	Mistral Medium 3.5 Mistral
Intelligence	14.2	14.2
Coding	31	Best: 46.9
Agentic	—	7
Speed	112 t/s	Best: 151 t/s
TTFT	2.49 s	Best: 2.21 s
Input · $ / 1M tokens	Best: $0.10	$1.50×15 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $0.30	$7.50×25 relative to the lowest price among the compared models
Context window	Best: 262K	256K
Reasoning	Yes	Yes
Open weights	Yes	Yes
Cost / task	—	$0.502

Intelligence

Gemma 4 12B (Reasoning): 14.2
Mistral Medium 3.5: 14.2

Coding

Gemma 4 12B (Reasoning): 31
Mistral Medium 3.5: Best: 46.9

Agentic

Gemma 4 12B (Reasoning): —
Mistral Medium 3.5: 7

Speed

Gemma 4 12B (Reasoning): 112 t/s
Mistral Medium 3.5: Best: 151 t/s

TTFT

Gemma 4 12B (Reasoning): 2.49 s
Mistral Medium 3.5: Best: 2.21 s

Input · $ / 1M tokens

Gemma 4 12B (Reasoning): Best: $0.10
Mistral Medium 3.5: $1.50×15 relative to the lowest price among the compared models

Output · $ / 1M tokens

Gemma 4 12B (Reasoning): Best: $0.30
Mistral Medium 3.5: $7.50×25 relative to the lowest price among the compared models

Context window

Gemma 4 12B (Reasoning): Best: 262K
Mistral Medium 3.5: 256K

Reasoning

Gemma 4 12B (Reasoning): Yes
Mistral Medium 3.5: Yes

Open weights

Gemma 4 12B (Reasoning): Yes
Mistral Medium 3.5: Yes

Cost / task

Gemma 4 12B (Reasoning): —
Mistral Medium 3.5: $0.502

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.

Gemma 4 12B (Reasoning)14.2 · $0.15
Mistral Medium 3.514.2 · $3