Model Comparator

Compare up to four models using the same criteria.

DeepSeek V3 (Dec '24)
DeepSeek
GLM-4.6V (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	DeepSeek V3 (Dec '24) DeepSeek	GLM-4.6V (Non-reasoning) Z.AI
Intelligence	Best: 8.5	8.4
Coding	23	—
Math	26	Best: 26.3
Agentic	0.8	—
Speed	37 t/s	Best: 82.1 t/s
TTFT	Best: 1.4 s	3.3 s
Input · $ / 1M tokens	$0.32×1.1 relative to the lowest price among the compared models	Best: $0.30
Output · $ / 1M tokens	Best: $0.89	$0.90
Context window	128K	128K
Reasoning	No	No
Open weights	Yes	Yes
Cost / task	$0.0198	—

Intelligence

DeepSeek V3 (Dec '24): Best: 8.5
GLM-4.6V (Non-reasoning): 8.4

Coding

DeepSeek V3 (Dec '24): 23
GLM-4.6V (Non-reasoning): —

Math

DeepSeek V3 (Dec '24): 26
GLM-4.6V (Non-reasoning): Best: 26.3

Agentic

DeepSeek V3 (Dec '24): 0.8
GLM-4.6V (Non-reasoning): —

Speed

DeepSeek V3 (Dec '24): 37 t/s
GLM-4.6V (Non-reasoning): Best: 82.1 t/s

TTFT

DeepSeek V3 (Dec '24): Best: 1.4 s
GLM-4.6V (Non-reasoning): 3.3 s

Input · $ / 1M tokens

DeepSeek V3 (Dec '24): $0.32×1.1 relative to the lowest price among the compared models
GLM-4.6V (Non-reasoning): Best: $0.30

Output · $ / 1M tokens

DeepSeek V3 (Dec '24): Best: $0.89
GLM-4.6V (Non-reasoning): $0.90

Context window

DeepSeek V3 (Dec '24): 128K
GLM-4.6V (Non-reasoning): 128K

Reasoning

DeepSeek V3 (Dec '24): No
GLM-4.6V (Non-reasoning): No

Open weights

DeepSeek V3 (Dec '24): Yes
GLM-4.6V (Non-reasoning): Yes

Cost / task

DeepSeek V3 (Dec '24): $0.0198
GLM-4.6V (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.

DeepSeek V3 (Dec '24)8.5 · $0.463
GLM-4.6V (Non-reasoning)8.4 · $0.45