Model Comparator

Compare up to four models using the same criteria.

GLM-4.5 (Reasoning)
Z.AI
Nemotron 3 Super 120B A12B (Reasoning)
NVIDIA

Differences only

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

Model Comparator
Metrics	GLM-4.5 (Reasoning) Z.AI	Nemotron 3 Super 120B A12B (Reasoning) NVIDIA
Intelligence	12.8	12.8
Coding	—	37.7
Math	73.7	—
Agentic	—	1.7
Speed	—	145 t/s
TTFT	—	1.13 s
Input · $ / 1M tokens	—	$0.30
Output · $ / 1M tokens	—	$0.90
Context window	128K	Best: 1M
Reasoning	Yes	Yes
Open weights	Yes	Yes
Cost / task	—	$1.64

Intelligence

GLM-4.5 (Reasoning): 12.8
Nemotron 3 Super 120B A12B (Reasoning): 12.8

Coding

GLM-4.5 (Reasoning): —
Nemotron 3 Super 120B A12B (Reasoning): 37.7

Math

GLM-4.5 (Reasoning): 73.7
Nemotron 3 Super 120B A12B (Reasoning): —

Agentic

GLM-4.5 (Reasoning): —
Nemotron 3 Super 120B A12B (Reasoning): 1.7

Speed

GLM-4.5 (Reasoning): —
Nemotron 3 Super 120B A12B (Reasoning): 145 t/s

TTFT

GLM-4.5 (Reasoning): —
Nemotron 3 Super 120B A12B (Reasoning): 1.13 s

Input · $ / 1M tokens

GLM-4.5 (Reasoning): —
Nemotron 3 Super 120B A12B (Reasoning): $0.30

Output · $ / 1M tokens

GLM-4.5 (Reasoning): —
Nemotron 3 Super 120B A12B (Reasoning): $0.90

Context window

GLM-4.5 (Reasoning): 128K
Nemotron 3 Super 120B A12B (Reasoning): Best: 1M

Reasoning

GLM-4.5 (Reasoning): Yes
Nemotron 3 Super 120B A12B (Reasoning): Yes

Open weights

GLM-4.5 (Reasoning): Yes
Nemotron 3 Super 120B A12B (Reasoning): Yes

Cost / task

GLM-4.5 (Reasoning): —
Nemotron 3 Super 120B A12B (Reasoning): $1.64

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.

Nemotron 3 Super 120B A12B (Reasoning)12.8 · $1.64

Not plotted for lack of data on these axes: GLM-4.5 (Reasoning).