Model Comparator

Compare up to four models using the same criteria.

Kimi K3.1 Pro
Moonshot AI
Grok 4.6 (High)
SpaceXSI

Differences only

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

Model Comparator
Metrics	Kimi K3.1 Pro Moonshot AI	Grok 4.6 (High) SpaceXSI
Intelligence	Best: 46.5	44.3
Coding	—	76.8
Agentic	—	53
Cyber Index	64.1%	—
Speed	28.8 t/s	Best: 66.5 t/s
TTFT	Best: 3.23 s	37 s
Input · $ / 1M tokens	$2	$2
Output · $ / 1M tokens	$10×1.7 relative to the lowest price among the compared models	Best: $6
Context window	1M	1M
Reasoning	Yes	Yes
Open weights	No	No
Cost / task	$3.68×2.5 relative to the lowest price among the compared models	Best: $1.48

Intelligence

Kimi K3.1 Pro: Best: 46.5
Grok 4.6 (High): 44.3

Coding

Kimi K3.1 Pro: —
Grok 4.6 (High): 76.8

Agentic

Kimi K3.1 Pro: —
Grok 4.6 (High): 53

Cyber Index

Kimi K3.1 Pro: 64.1%
Grok 4.6 (High): —

Speed

Kimi K3.1 Pro: 28.8 t/s
Grok 4.6 (High): Best: 66.5 t/s

TTFT

Kimi K3.1 Pro: Best: 3.23 s
Grok 4.6 (High): 37 s

Input · $ / 1M tokens

Kimi K3.1 Pro: $2
Grok 4.6 (High): $2

Output · $ / 1M tokens

Kimi K3.1 Pro: $10×1.7 relative to the lowest price among the compared models
Grok 4.6 (High): Best: $6

Context window

Kimi K3.1 Pro: 1M
Grok 4.6 (High): 1M

Reasoning

Kimi K3.1 Pro: Yes
Grok 4.6 (High): Yes

Open weights

Kimi K3.1 Pro: No
Grok 4.6 (High): No

Cost / task

Kimi K3.1 Pro: $3.68×2.5 relative to the lowest price among the compared models
Grok 4.6 (High): Best: $1.48

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.

Kimi K3.1 Pro46.5 · $3.68
Grok 4.6 (High)44.3 · $1.48