Model Comparator

Compare up to four models using the same criteria.

Claude Opus 4.6 (batch)
Anthropic
GLM-5.3 (Max)
Z.AI

Differences only

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

Model Comparator
Metrics	Claude Opus 4.6 (batch) Anthropic	GLM-5.3 (Max) Z.AI
Intelligence	Best: 31.9	31.7
Coding	—	74.8
Agentic	—	53.1
Cyber Index	—	36.4%
Speed	—	80.1 t/s
TTFT	—	1.75 s
Input · $ / 1M tokens	$2.50×1.8 relative to the lowest price among the compared models	Best: $1.40
Output · $ / 1M tokens	$12.50×2.8 relative to the lowest price among the compared models	Best: $4.40
Context window	1M	1M
Reasoning	Yes	Yes
Open weights	—	Yes
Cost / task	—	$5.01

Intelligence

Claude Opus 4.6 (batch): Best: 31.9
GLM-5.3 (Max): 31.7

Coding

Claude Opus 4.6 (batch): —
GLM-5.3 (Max): 74.8

Agentic

Claude Opus 4.6 (batch): —
GLM-5.3 (Max): 53.1

Cyber Index

Claude Opus 4.6 (batch): —
GLM-5.3 (Max): 36.4%

Speed

Claude Opus 4.6 (batch): —
GLM-5.3 (Max): 80.1 t/s

TTFT

Claude Opus 4.6 (batch): —
GLM-5.3 (Max): 1.75 s

Input · $ / 1M tokens

Claude Opus 4.6 (batch): $2.50×1.8 relative to the lowest price among the compared models
GLM-5.3 (Max): Best: $1.40

Output · $ / 1M tokens

Claude Opus 4.6 (batch): $12.50×2.8 relative to the lowest price among the compared models
GLM-5.3 (Max): Best: $4.40

Context window

Claude Opus 4.6 (batch): 1M
GLM-5.3 (Max): 1M

Reasoning

Claude Opus 4.6 (batch): Yes
GLM-5.3 (Max): Yes

Open weights

Claude Opus 4.6 (batch): —
GLM-5.3 (Max): Yes

Cost / task

Claude Opus 4.6 (batch): —
GLM-5.3 (Max): $5.01

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.

Claude Opus 4.6 (batch)31.9 · $5
GLM-5.3 (Max)31.7 · $2.15