Model Comparator

Compare up to four models using the same criteria.

Devstral Small (Jul '25)
Mistral
GLM-4.5V (Non-reasoning)
Z.AI

Differences only

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

Model Comparator
Metrics	Devstral Small (Jul '25) Mistral	GLM-4.5V (Non-reasoning) Z.AI
Intelligence	7.6	7.6
Math	Best: 29.3	15.3
Speed	—	64.4 t/s
TTFT	—	3.44 s
Input · $ / 1M tokens	—	$0.60
Output · $ / 1M tokens	—	$1.80
Context window	256K	Best: 1M
Reasoning	No	No
Open weights	Yes	Yes

Intelligence

Devstral Small (Jul '25): 7.6
GLM-4.5V (Non-reasoning): 7.6

Math

Devstral Small (Jul '25): Best: 29.3
GLM-4.5V (Non-reasoning): 15.3

Speed

Devstral Small (Jul '25): —
GLM-4.5V (Non-reasoning): 64.4 t/s

TTFT

Devstral Small (Jul '25): —
GLM-4.5V (Non-reasoning): 3.44 s

Input · $ / 1M tokens

Devstral Small (Jul '25): —
GLM-4.5V (Non-reasoning): $0.60

Output · $ / 1M tokens

Devstral Small (Jul '25): —
GLM-4.5V (Non-reasoning): $1.80

Context window

Devstral Small (Jul '25): 256K
GLM-4.5V (Non-reasoning): Best: 1M

Reasoning

Devstral Small (Jul '25): No
GLM-4.5V (Non-reasoning): No

Open weights

Devstral Small (Jul '25): Yes
GLM-4.5V (Non-reasoning): Yes

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.

GLM-4.5V (Non-reasoning)7.6 · $0.90

Not plotted for lack of data on these axes: Devstral Small (Jul '25).