Model Comparator

Compare up to four models using the same criteria.

Gemma 4 31B (Reasoning)
Google
GLM-4.6 (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	Gemma 4 31B (Reasoning) Google	GLM-4.6 (Non-reasoning) Z.AI
Intelligence	14.7	Best: 14.9
Coding	43.4	—
Math	—	44.3
Agentic	4.2	—
Speed	Best: 35.5 t/s	32.4 t/s
TTFT	Best: 1.03 s	4.64 s
Input · $ / 1M tokens	—	$0.575
Output · $ / 1M tokens	—	$2.20
Context window	Best: 256K	200K
Reasoning	Yes	No
Open weights	Yes	Yes
Cost / task	$0	—

Intelligence

Gemma 4 31B (Reasoning): 14.7
GLM-4.6 (Non-reasoning): Best: 14.9

Coding

Gemma 4 31B (Reasoning): 43.4
GLM-4.6 (Non-reasoning): —

Math

Gemma 4 31B (Reasoning): —
GLM-4.6 (Non-reasoning): 44.3

Agentic

Gemma 4 31B (Reasoning): 4.2
GLM-4.6 (Non-reasoning): —

Speed

Gemma 4 31B (Reasoning): Best: 35.5 t/s
GLM-4.6 (Non-reasoning): 32.4 t/s

TTFT

Gemma 4 31B (Reasoning): Best: 1.03 s
GLM-4.6 (Non-reasoning): 4.64 s

Input · $ / 1M tokens

Gemma 4 31B (Reasoning): —
GLM-4.6 (Non-reasoning): $0.575

Output · $ / 1M tokens

Gemma 4 31B (Reasoning): —
GLM-4.6 (Non-reasoning): $2.20

Context window

Gemma 4 31B (Reasoning): Best: 256K
GLM-4.6 (Non-reasoning): 200K

Reasoning

Gemma 4 31B (Reasoning): Yes
GLM-4.6 (Non-reasoning): No

Open weights

Gemma 4 31B (Reasoning): Yes
GLM-4.6 (Non-reasoning): Yes

Cost / task

Gemma 4 31B (Reasoning): $0
GLM-4.6 (Non-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.

Gemma 4 31B (Reasoning)14.7 · 35.5 t/s
GLM-4.6 (Non-reasoning)14.9 · 32.4 t/s