Model Comparator

Compare up to four models using the same criteria.

Grok 4.6 (Medium)
SpaceXSI
GPT-5.6 Terra (Max)
OpenAI

Differences only

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

Model Comparator
Metrics	Grok 4.6 (Medium) SpaceXSI	GPT-5.6 Terra (Max) OpenAI
Intelligence	Best: 42.8	42.1
Coding	74.4	Best: 76.7
Agentic	Best: 50.6	43.2
Speed	52 t/s	Best: 107 t/s
TTFT	Best: 34.7 s	137 s
Input · $ / 1M tokens	$2	$2
Output · $ / 1M tokens	Best: $6	$12×2 relative to the lowest price among the compared models
Context window	500K	Best: 1M
Reasoning	Yes	Yes
Open weights	No	No
Cost / task	Best: $1.14	$1.40×1.2 relative to the lowest price among the compared models

Intelligence

Grok 4.6 (Medium): Best: 42.8
GPT-5.6 Terra (Max): 42.1

Coding

Grok 4.6 (Medium): 74.4
GPT-5.6 Terra (Max): Best: 76.7

Agentic

Grok 4.6 (Medium): Best: 50.6
GPT-5.6 Terra (Max): 43.2

Speed

Grok 4.6 (Medium): 52 t/s
GPT-5.6 Terra (Max): Best: 107 t/s

TTFT

Grok 4.6 (Medium): Best: 34.7 s
GPT-5.6 Terra (Max): 137 s

Input · $ / 1M tokens

Grok 4.6 (Medium): $2
GPT-5.6 Terra (Max): $2

Output · $ / 1M tokens

Grok 4.6 (Medium): Best: $6
GPT-5.6 Terra (Max): $12×2 relative to the lowest price among the compared models

Context window

Grok 4.6 (Medium): 500K
GPT-5.6 Terra (Max): Best: 1M

Reasoning

Grok 4.6 (Medium): Yes
GPT-5.6 Terra (Max): Yes

Open weights

Grok 4.6 (Medium): No
GPT-5.6 Terra (Max): No

Cost / task

Grok 4.6 (Medium): Best: $1.14
GPT-5.6 Terra (Max): $1.40×1.2 relative to the lowest price among the compared models

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 4.6 (Medium)42.8 · $1.14
GPT-5.6 Terra (Max)42.1 · $1.40