Model Comparator

Compare up to four models using the same criteria.

Claude Sonnet 5 (Max)
Anthropic
GPT-5.4 (Xhigh)
OpenAI

Differences only

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

Model Comparator
Metrics	Claude Sonnet 5 (Max) Anthropic	GPT-5.4 (Xhigh) OpenAI
Intelligence	38.2	Best: 39
Coding	Best: 71.5	71.1
Agentic	43.6	—
Speed	75.6 t/s	Best: 86.1 t/s
TTFT	Best: 218 s	229 s
Input · $ / 1M tokens	Best: $2	$2.50×1.3 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $10	$15×1.5 relative to the lowest price among the compared models
Context window	1M	Best: 1.1M
Reasoning	Yes	Yes
Open weights	No	No
Cost / task	$5.09	—

Intelligence

Claude Sonnet 5 (Max): 38.2
GPT-5.4 (Xhigh): Best: 39

Coding

Claude Sonnet 5 (Max): Best: 71.5
GPT-5.4 (Xhigh): 71.1

Agentic

Claude Sonnet 5 (Max): 43.6
GPT-5.4 (Xhigh): —

Speed

Claude Sonnet 5 (Max): 75.6 t/s
GPT-5.4 (Xhigh): Best: 86.1 t/s

TTFT

Claude Sonnet 5 (Max): Best: 218 s
GPT-5.4 (Xhigh): 229 s

Input · $ / 1M tokens

Claude Sonnet 5 (Max): Best: $2
GPT-5.4 (Xhigh): $2.50×1.3 relative to the lowest price among the compared models

Output · $ / 1M tokens

Claude Sonnet 5 (Max): Best: $10
GPT-5.4 (Xhigh): $15×1.5 relative to the lowest price among the compared models

Context window

Claude Sonnet 5 (Max): 1M
GPT-5.4 (Xhigh): Best: 1.1M

Reasoning

Claude Sonnet 5 (Max): Yes
GPT-5.4 (Xhigh): Yes

Open weights

Claude Sonnet 5 (Max): No
GPT-5.4 (Xhigh): No

Cost / task

Claude Sonnet 5 (Max): $5.09
GPT-5.4 (Xhigh): —

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 Sonnet 5 (Max)38.2 · $4
GPT-5.4 (Xhigh)39 · $5.63