Model Comparator

Compare up to four models using the same criteria.

Grok Build 0.1 0616
SpaceXSI
Kimi K2.6 (Reasoning)
Moonshot AI

Differences only

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

Model Comparator
Metrics	Grok Build 0.1 0616 SpaceXSI	Kimi K2.6 (Reasoning) Moonshot AI
Intelligence	Best: 27.2	27
Coding	51.5	Best: 61.8
Agentic	—	20.5
Speed	Best: 67.4 t/s	52.8 t/s
TTFT	Best: 1.81 s	2.9 s
Input · $ / 1M tokens	$1×1.1 relative to the lowest price among the compared models	Best: $0.95
Output · $ / 1M tokens	Best: $2	$4×2 relative to the lowest price among the compared models
Context window	256K	256K
Reasoning	Yes	Yes
Open weights	No	Yes
Cost / task	—	$0.80

Intelligence

Grok Build 0.1 0616: Best: 27.2
Kimi K2.6 (Reasoning): 27

Coding

Grok Build 0.1 0616: 51.5
Kimi K2.6 (Reasoning): Best: 61.8

Agentic

Grok Build 0.1 0616: —
Kimi K2.6 (Reasoning): 20.5

Speed

Grok Build 0.1 0616: Best: 67.4 t/s
Kimi K2.6 (Reasoning): 52.8 t/s

TTFT

Grok Build 0.1 0616: Best: 1.81 s
Kimi K2.6 (Reasoning): 2.9 s

Input · $ / 1M tokens

Grok Build 0.1 0616: $1×1.1 relative to the lowest price among the compared models
Kimi K2.6 (Reasoning): Best: $0.95

Output · $ / 1M tokens

Grok Build 0.1 0616: Best: $2
Kimi K2.6 (Reasoning): $4×2 relative to the lowest price among the compared models

Context window

Grok Build 0.1 0616: 256K
Kimi K2.6 (Reasoning): 256K

Reasoning

Grok Build 0.1 0616: Yes
Kimi K2.6 (Reasoning): Yes

Open weights

Grok Build 0.1 0616: No
Kimi K2.6 (Reasoning): Yes

Cost / task

Grok Build 0.1 0616: —
Kimi K2.6 (Reasoning): $0.80

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 Build 0.1 061627.2 · $1.25
Kimi K2.6 (Reasoning)27 · $1.71