Model Comparator

Compare up to four models using the same criteria.

GPT-6 Luna (High)
OpenAI
DeepSeek V3.2 (Non-reasoning)
DeepSeek

Differences only

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

Model Comparator
Metrics	GPT-6 Luna (High) OpenAI	DeepSeek V3.2 (Non-reasoning) DeepSeek
Intelligence	21.4	Best: 21.5
Coding	—	44.2
Math	—	59
Speed	114 t/s	—
TTFT	19.2 s	—
Input · $ / 1M tokens	Best: $0.10	$0.28×2.8 relative to the lowest price among the compared models
Output · $ / 1M tokens	$0.50×1.2 relative to the lowest price among the compared models	Best: $0.42
Context window	1M	1M
Reasoning	Yes	No
Open weights	No	Yes
Cost / task	$0.0729	—

Intelligence

GPT-6 Luna (High): 21.4
DeepSeek V3.2 (Non-reasoning): Best: 21.5

Coding

GPT-6 Luna (High): —
DeepSeek V3.2 (Non-reasoning): 44.2

Math

GPT-6 Luna (High): —
DeepSeek V3.2 (Non-reasoning): 59

Speed

GPT-6 Luna (High): 114 t/s
DeepSeek V3.2 (Non-reasoning): —

TTFT

GPT-6 Luna (High): 19.2 s
DeepSeek V3.2 (Non-reasoning): —

Input · $ / 1M tokens

GPT-6 Luna (High): Best: $0.10
DeepSeek V3.2 (Non-reasoning): $0.28×2.8 relative to the lowest price among the compared models

Output · $ / 1M tokens

GPT-6 Luna (High): $0.50×1.2 relative to the lowest price among the compared models
DeepSeek V3.2 (Non-reasoning): Best: $0.42

Context window

GPT-6 Luna (High): 1M
DeepSeek V3.2 (Non-reasoning): 1M

Reasoning

GPT-6 Luna (High): Yes
DeepSeek V3.2 (Non-reasoning): No

Open weights

GPT-6 Luna (High): No
DeepSeek V3.2 (Non-reasoning): Yes

Cost / task

GPT-6 Luna (High): $0.0729
DeepSeek V3.2 (Non-reasoning): —

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-6 Luna (High)21.4 · $0.20
DeepSeek V3.2 (Non-reasoning)21.5 · $0.315