Model Comparator

Compare up to four models using the same criteria.

Kimi K3 (Low)
Moonshot AI
GPT-5.2 (Xhigh)
OpenAI

Differences only

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

Model Comparator
Metrics	Kimi K3 (Low) Moonshot AI	GPT-5.2 (Xhigh) OpenAI
Intelligence	30.1	Best: 30.4
Coding	72	—
Math	—	99
Agentic	29.3	—
Speed	44.2 t/s	Best: 75.6 t/s
TTFT	Best: 3.38 s	81.3 s
Input · $ / 1M tokens	$3×1.7 relative to the lowest price among the compared models	Best: $1.75
Output · $ / 1M tokens	$15×1.1 relative to the lowest price among the compared models	Best: $14
Context window	Best: 1M	400K
Reasoning	Yes	Yes
Open weights	Yes	No
Cost / task	$1.15	—

Intelligence

Kimi K3 (Low): 30.1
GPT-5.2 (Xhigh): Best: 30.4

Coding

Kimi K3 (Low): 72
GPT-5.2 (Xhigh): —

Math

Kimi K3 (Low): —
GPT-5.2 (Xhigh): 99

Agentic

Kimi K3 (Low): 29.3
GPT-5.2 (Xhigh): —

Speed

Kimi K3 (Low): 44.2 t/s
GPT-5.2 (Xhigh): Best: 75.6 t/s

TTFT

Kimi K3 (Low): Best: 3.38 s
GPT-5.2 (Xhigh): 81.3 s

Input · $ / 1M tokens

Kimi K3 (Low): $3×1.7 relative to the lowest price among the compared models
GPT-5.2 (Xhigh): Best: $1.75

Output · $ / 1M tokens

Kimi K3 (Low): $15×1.1 relative to the lowest price among the compared models
GPT-5.2 (Xhigh): Best: $14

Context window

Kimi K3 (Low): Best: 1M
GPT-5.2 (Xhigh): 400K

Reasoning

Kimi K3 (Low): Yes
GPT-5.2 (Xhigh): Yes

Open weights

Kimi K3 (Low): Yes
GPT-5.2 (Xhigh): No

Cost / task

Kimi K3 (Low): $1.15
GPT-5.2 (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.

Kimi K3 (Low)30.1 · $6
GPT-5.2 (Xhigh)30.4 · $4.81