Model Comparator

Compare up to four models using the same criteria.

Claude 4.5 Sonnet (Reasoning)
Anthropic
GPT-5 Mini (batch)
OpenAI

Differences only

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

Model Comparator
Metrics	Claude 4.5 Sonnet (Reasoning) Anthropic	GPT-5 Mini (batch) OpenAI
Intelligence	Best: 20.7	20.6
Coding	Best: 52.1	15.6
Math	88	—
Agentic	Best: 15.8	6.8
Speed	44.1 t/s	—
TTFT	14.1 s	—
Input · $ / 1M tokens	$3	—
Output · $ / 1M tokens	$15	—
Context window	Best: 1M	400K
Reasoning	Yes	Yes
Open weights	No	—
Cost / task	$0.557	—

Intelligence

Claude 4.5 Sonnet (Reasoning): Best: 20.7
GPT-5 Mini (batch): 20.6

Coding

Claude 4.5 Sonnet (Reasoning): Best: 52.1
GPT-5 Mini (batch): 15.6

Math

Claude 4.5 Sonnet (Reasoning): 88
GPT-5 Mini (batch): —

Agentic

Claude 4.5 Sonnet (Reasoning): Best: 15.8
GPT-5 Mini (batch): 6.8

Speed

Claude 4.5 Sonnet (Reasoning): 44.1 t/s
GPT-5 Mini (batch): —

TTFT

Claude 4.5 Sonnet (Reasoning): 14.1 s
GPT-5 Mini (batch): —

Input · $ / 1M tokens

Claude 4.5 Sonnet (Reasoning): $3
GPT-5 Mini (batch): —

Output · $ / 1M tokens

Claude 4.5 Sonnet (Reasoning): $15
GPT-5 Mini (batch): —

Context window

Claude 4.5 Sonnet (Reasoning): Best: 1M
GPT-5 Mini (batch): 400K

Reasoning

Claude 4.5 Sonnet (Reasoning): Yes
GPT-5 Mini (batch): Yes

Open weights

Claude 4.5 Sonnet (Reasoning): No
GPT-5 Mini (batch): —

Cost / task

Claude 4.5 Sonnet (Reasoning): $0.557
GPT-5 Mini (batch): —

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 4.5 Sonnet (Reasoning)20.7 · $0.557

Not plotted for lack of data on these axes: GPT-5 Mini (batch).