Model Comparator

Compare up to four models using the same criteria.

GPT-5.3 Codex (Xhigh)
OpenAI
Gemini 3.5 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-5.3 Codex (Xhigh) OpenAI	Gemini 3.5 Flash (High) Google
Intelligence	32.5	Best: 32.6
Coding	—	70.1
Agentic	—	26
Speed	98.5 t/s	Best: 177 t/s
TTFT	71.5 s	Best: 14.7 s
Input · $ / 1M tokens	$1.75×1.2 relative to the lowest price among the compared models	Best: $1.50
Output · $ / 1M tokens	$14×1.6 relative to the lowest price among the compared models	Best: $9
Context window	400K	Best: 1M
Reasoning	Yes	Yes
Open weights	No	No
Cost / task	—	$3.69

Intelligence

GPT-5.3 Codex (Xhigh): 32.5
Gemini 3.5 Flash (High): Best: 32.6

Coding

GPT-5.3 Codex (Xhigh): —
Gemini 3.5 Flash (High): 70.1

Agentic

GPT-5.3 Codex (Xhigh): —
Gemini 3.5 Flash (High): 26

Speed

GPT-5.3 Codex (Xhigh): 98.5 t/s
Gemini 3.5 Flash (High): Best: 177 t/s

TTFT

GPT-5.3 Codex (Xhigh): 71.5 s
Gemini 3.5 Flash (High): Best: 14.7 s

Input · $ / 1M tokens

GPT-5.3 Codex (Xhigh): $1.75×1.2 relative to the lowest price among the compared models
Gemini 3.5 Flash (High): Best: $1.50

Output · $ / 1M tokens

GPT-5.3 Codex (Xhigh): $14×1.6 relative to the lowest price among the compared models
Gemini 3.5 Flash (High): Best: $9

Context window

GPT-5.3 Codex (Xhigh): 400K
Gemini 3.5 Flash (High): Best: 1M

Reasoning

GPT-5.3 Codex (Xhigh): Yes
Gemini 3.5 Flash (High): Yes

Open weights

GPT-5.3 Codex (Xhigh): No
Gemini 3.5 Flash (High): No

Cost / task

GPT-5.3 Codex (Xhigh): —
Gemini 3.5 Flash (High): $3.69

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-5.3 Codex (Xhigh)32.5 · $4.81
Gemini 3.5 Flash (High)32.6 · $3.38