Model Comparator

Compare up to four models using the same criteria.

Grok 4.3 (High)
SpaceXSI
GPT-5 Codex (High)
OpenAI

Differences only

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

Model Comparator
Metrics	Grok 4.3 (High) SpaceXSI	GPT-5 Codex (High) OpenAI
Intelligence	24.9	24.9
Coding	42.2	—
Math	—	98.7
Agentic	15.5	—
Speed	94.6 t/s	Best: 166 t/s
TTFT	24.8 s	Best: 6.71 s
Input · $ / 1M tokens	$1.25	$1.25
Output · $ / 1M tokens	Best: $2.50	$10×4 relative to the lowest price among the compared models
Context window	Best: 1M	400K
Reasoning	Yes	Yes
Open weights	No	No
Cost / task	$0.205	—

Intelligence

Grok 4.3 (High): 24.9
GPT-5 Codex (High): 24.9

Coding

Grok 4.3 (High): 42.2
GPT-5 Codex (High): —

Math

Grok 4.3 (High): —
GPT-5 Codex (High): 98.7

Agentic

Grok 4.3 (High): 15.5
GPT-5 Codex (High): —

Speed

Grok 4.3 (High): 94.6 t/s
GPT-5 Codex (High): Best: 166 t/s

TTFT

Grok 4.3 (High): 24.8 s
GPT-5 Codex (High): Best: 6.71 s

Input · $ / 1M tokens

Grok 4.3 (High): $1.25
GPT-5 Codex (High): $1.25

Output · $ / 1M tokens

Grok 4.3 (High): Best: $2.50
GPT-5 Codex (High): $10×4 relative to the lowest price among the compared models

Context window

Grok 4.3 (High): Best: 1M
GPT-5 Codex (High): 400K

Reasoning

Grok 4.3 (High): Yes
GPT-5 Codex (High): Yes

Open weights

Grok 4.3 (High): No
GPT-5 Codex (High): No

Cost / task

Grok 4.3 (High): $0.205
GPT-5 Codex (High): —

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.

Grok 4.3 (High)24.9 · $1.56
GPT-5 Codex (High)24.9 · $3.44