Model Comparator

Compare up to four models using the same criteria.

GPT-5.4 (Xhigh)
OpenAI
Gemini 3.7 Flash (High)
Google

Differences only

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

Model Comparator
Metrics	GPT-5.4 (Xhigh) OpenAI	Gemini 3.7 Flash (High) Google
Intelligence	39	Best: 39.1
Coding	71.1	Best: 76.1
Agentic	—	35.2
Speed	85.5 t/s	Best: 299 t/s
TTFT	178 s	Best: 8.42 s
Input · $ / 1M tokens	$2.50×3.3 relative to the lowest price among the compared models	Best: $0.75
Output · $ / 1M tokens	$15×4 relative to the lowest price among the compared models	Best: $3.75
Context window	Best: 1.1M	1M
Reasoning	Yes	Yes
Open weights	No	No
Cost / task	—	$0.925

Intelligence

GPT-5.4 (Xhigh): 39
Gemini 3.7 Flash (High): Best: 39.1

Coding

GPT-5.4 (Xhigh): 71.1
Gemini 3.7 Flash (High): Best: 76.1

Agentic

GPT-5.4 (Xhigh): —
Gemini 3.7 Flash (High): 35.2

Speed

GPT-5.4 (Xhigh): 85.5 t/s
Gemini 3.7 Flash (High): Best: 299 t/s

TTFT

GPT-5.4 (Xhigh): 178 s
Gemini 3.7 Flash (High): Best: 8.42 s

Input · $ / 1M tokens

GPT-5.4 (Xhigh): $2.50×3.3 relative to the lowest price among the compared models
Gemini 3.7 Flash (High): Best: $0.75

Output · $ / 1M tokens

GPT-5.4 (Xhigh): $15×4 relative to the lowest price among the compared models
Gemini 3.7 Flash (High): Best: $3.75

Context window

GPT-5.4 (Xhigh): Best: 1.1M
Gemini 3.7 Flash (High): 1M

Reasoning

GPT-5.4 (Xhigh): Yes
Gemini 3.7 Flash (High): Yes

Open weights

GPT-5.4 (Xhigh): No
Gemini 3.7 Flash (High): No

Cost / task

GPT-5.4 (Xhigh): —
Gemini 3.7 Flash (High): $0.925

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-5.4 (Xhigh)39 · $5.63
Gemini 3.7 Flash (High)39.1 · $1.50