Model Comparator

Compare up to four models using the same criteria.

Mistral Large 4 Preview
Mistral
Grok 4.20 0309 (Reasoning)
SpaceXSI

Differences only

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

Model Comparator
Metrics	Mistral Large 4 Preview Mistral	Grok 4.20 0309 (Reasoning) SpaceXSI
Intelligence	Best: 25.3	25.2
Cyber Index	49.5%	—
Speed	111 t/s	—
TTFT	1.92 s	—
Input · $ / 1M tokens	Best: $1.36	$2×1.5 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $4.18	$6×1.4 relative to the lowest price among the compared models
Context window	524K	Best: 2M
Reasoning	Yes	Yes
Open weights	No	No
Cost / task	$5.54	—

Intelligence

Mistral Large 4 Preview: Best: 25.3
Grok 4.20 0309 (Reasoning): 25.2

Cyber Index

Mistral Large 4 Preview: 49.5%
Grok 4.20 0309 (Reasoning): —

Speed

Mistral Large 4 Preview: 111 t/s
Grok 4.20 0309 (Reasoning): —

TTFT

Mistral Large 4 Preview: 1.92 s
Grok 4.20 0309 (Reasoning): —

Input · $ / 1M tokens

Mistral Large 4 Preview: Best: $1.36
Grok 4.20 0309 (Reasoning): $2×1.5 relative to the lowest price among the compared models

Output · $ / 1M tokens

Mistral Large 4 Preview: Best: $4.18
Grok 4.20 0309 (Reasoning): $6×1.4 relative to the lowest price among the compared models

Context window

Mistral Large 4 Preview: 524K
Grok 4.20 0309 (Reasoning): Best: 2M

Reasoning

Mistral Large 4 Preview: Yes
Grok 4.20 0309 (Reasoning): Yes

Open weights

Mistral Large 4 Preview: No
Grok 4.20 0309 (Reasoning): No

Cost / task

Mistral Large 4 Preview: $5.54
Grok 4.20 0309 (Reasoning): —

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 4 Preview25.3 · $2.07
Grok 4.20 0309 (Reasoning)25.2 · $3