Model Comparator

Compare up to four models using the same criteria.

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

Differences only

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

Model Comparator
Metrics	GPT-5 Mini (batch) OpenAI	Claude 4.5 Sonnet (Non-reasoning) Anthropic
Intelligence	20.6	Best: 20.7
Coding	15.6	Best: 52.1
Math	—	37
Agentic	6.8	Best: 15.8
Speed	—	39.3 t/s
TTFT	—	1.02 s
Input · $ / 1M tokens	—	$3
Output · $ / 1M tokens	—	$15
Context window	400K	Best: 1M
Reasoning	Yes	No
Open weights	—	No

Intelligence

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

Coding

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

Math

GPT-5 Mini (batch): —
Claude 4.5 Sonnet (Non-reasoning): 37

Agentic

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

Speed

GPT-5 Mini (batch): —
Claude 4.5 Sonnet (Non-reasoning): 39.3 t/s

TTFT

GPT-5 Mini (batch): —
Claude 4.5 Sonnet (Non-reasoning): 1.02 s

Input · $ / 1M tokens

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

Output · $ / 1M tokens

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

Context window

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

Reasoning

GPT-5 Mini (batch): Yes
Claude 4.5 Sonnet (Non-reasoning): No

Open weights

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

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 (Non-reasoning)20.7 · $6

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