Model Comparator

Compare up to four models using the same criteria.

GPT-5.2 (Xhigh)
OpenAI
Gemini 3.1 Pro Preview
Google

Differences only

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

Model Comparator
Metrics	GPT-5.2 (Xhigh) OpenAI	Gemini 3.1 Pro Preview Google
Intelligence	Best: 30.4	29.7
Coding	—	68.8
Math	99	—
Agentic	—	8.2
Speed	73.3 t/s	Best: 131 t/s
TTFT	125 s	Best: 20.8 s
Input · $ / 1M tokens	Best: $1.75	$2×1.1 relative to the lowest price among the compared models
Output · $ / 1M tokens	$14×1.2 relative to the lowest price among the compared models	Best: $12
Context window	400K	Best: 1M
Reasoning	Yes	Yes
Open weights	No	No
Cost / task	—	$1.30

Intelligence

GPT-5.2 (Xhigh): Best: 30.4
Gemini 3.1 Pro Preview: 29.7

Coding

GPT-5.2 (Xhigh): —
Gemini 3.1 Pro Preview: 68.8

Math

GPT-5.2 (Xhigh): 99
Gemini 3.1 Pro Preview: —

Agentic

GPT-5.2 (Xhigh): —
Gemini 3.1 Pro Preview: 8.2

Speed

GPT-5.2 (Xhigh): 73.3 t/s
Gemini 3.1 Pro Preview: Best: 131 t/s

TTFT

GPT-5.2 (Xhigh): 125 s
Gemini 3.1 Pro Preview: Best: 20.8 s

Input · $ / 1M tokens

GPT-5.2 (Xhigh): Best: $1.75
Gemini 3.1 Pro Preview: $2×1.1 relative to the lowest price among the compared models

Output · $ / 1M tokens

GPT-5.2 (Xhigh): $14×1.2 relative to the lowest price among the compared models
Gemini 3.1 Pro Preview: Best: $12

Context window

GPT-5.2 (Xhigh): 400K
Gemini 3.1 Pro Preview: Best: 1M

Reasoning

GPT-5.2 (Xhigh): Yes
Gemini 3.1 Pro Preview: Yes

Open weights

GPT-5.2 (Xhigh): No
Gemini 3.1 Pro Preview: No

Cost / task

GPT-5.2 (Xhigh): —
Gemini 3.1 Pro Preview: $1.30

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.

GPT-5.2 (Xhigh)30.4 · $4.81
Gemini 3.1 Pro Preview29.7 · $4.50