Model Comparator

Compare up to four models using the same criteria.

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

Differences only

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

Model Comparator
Metrics	Nemotron 3 Super 120B A12B (Reasoning) NVIDIA	GLM-4.5 (Reasoning) Z.AI
Intelligence	12.8	12.8
Coding	37.7	—
Math	—	73.7
Agentic	1.7	—
Speed	146 t/s	—
TTFT	1.31 s	—
Input · $ / 1M tokens	$0.30	—
Output · $ / 1M tokens	$0.90	—
Context window	Best: 1M	128K
Reasoning	Yes	Yes
Open weights	Yes	Yes
Cost / task	$1.64	—

Intelligence

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

Coding

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

Math

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

Agentic

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

Speed

Nemotron 3 Super 120B A12B (Reasoning): 146 t/s
GLM-4.5 (Reasoning): —

TTFT

Nemotron 3 Super 120B A12B (Reasoning): 1.31 s
GLM-4.5 (Reasoning): —

Input · $ / 1M tokens

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

Output · $ / 1M tokens

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

Context window

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

Reasoning

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

Open weights

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

Cost / task

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

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

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