Model Comparator

Compare up to four models using the same criteria.

Step 5 Preview
StepFun
GPT-5.2 Codex (Xhigh)
OpenAI

Differences only

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

Model Comparator
Metrics	Step 5 Preview StepFun	GPT-5.2 Codex (Xhigh) OpenAI
Intelligence	28.5	28.5
Cyber Index	47.7%	—
Speed	Best: 141 t/s	99.9 t/s
TTFT	Best: 0.92 s	178 s
Input · $ / 1M tokens	Best: $1	$1.75×1.8 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $2.70	$14×5.2 relative to the lowest price among the compared models
Context window	1M	1M
Reasoning	Yes	Yes
Open weights	Yes	No
Cost / task	$2.35	—

Intelligence

Step 5 Preview: 28.5
GPT-5.2 Codex (Xhigh): 28.5

Cyber Index

Step 5 Preview: 47.7%
GPT-5.2 Codex (Xhigh): —

Speed

Step 5 Preview: Best: 141 t/s
GPT-5.2 Codex (Xhigh): 99.9 t/s

TTFT

Step 5 Preview: Best: 0.92 s
GPT-5.2 Codex (Xhigh): 178 s

Input · $ / 1M tokens

Step 5 Preview: Best: $1
GPT-5.2 Codex (Xhigh): $1.75×1.8 relative to the lowest price among the compared models

Output · $ / 1M tokens

Step 5 Preview: Best: $2.70
GPT-5.2 Codex (Xhigh): $14×5.2 relative to the lowest price among the compared models

Context window

Step 5 Preview: 1M
GPT-5.2 Codex (Xhigh): 1M

Reasoning

Step 5 Preview: Yes
GPT-5.2 Codex (Xhigh): Yes

Open weights

Step 5 Preview: Yes
GPT-5.2 Codex (Xhigh): No

Cost / task

Step 5 Preview: $2.35
GPT-5.2 Codex (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.

Step 5 Preview28.5 · $1.43
GPT-5.2 Codex (Xhigh)28.5 · $4.81