Model Comparator

Compare up to four models using the same criteria.

Kimi K2.6 (Non-reasoning)
Moonshot AI
Kimi K2.5 (Reasoning)
Moonshot AI

Differences only

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

Model Comparator
Metrics	Kimi K2.6 (Non-reasoning) Moonshot AI	Kimi K2.5 (Reasoning) Moonshot AI
Intelligence	Best: 23.6	23.5
Coding	—	46.8
Speed	45.5 t/s	Best: 60 t/s
TTFT	2.78 s	Best: 1.85 s
Input · $ / 1M tokens	$0.95×1.6 relative to the lowest price among the compared models	Best: $0.60
Output · $ / 1M tokens	$4×1.5 relative to the lowest price among the compared models	Best: $2.75
Context window	256K	256K
Reasoning	No	Yes
Open weights	Yes	Yes

Intelligence

Kimi K2.6 (Non-reasoning): Best: 23.6
Kimi K2.5 (Reasoning): 23.5

Coding

Kimi K2.6 (Non-reasoning): —
Kimi K2.5 (Reasoning): 46.8

Speed

Kimi K2.6 (Non-reasoning): 45.5 t/s
Kimi K2.5 (Reasoning): Best: 60 t/s

TTFT

Kimi K2.6 (Non-reasoning): 2.78 s
Kimi K2.5 (Reasoning): Best: 1.85 s

Input · $ / 1M tokens

Kimi K2.6 (Non-reasoning): $0.95×1.6 relative to the lowest price among the compared models
Kimi K2.5 (Reasoning): Best: $0.60

Output · $ / 1M tokens

Kimi K2.6 (Non-reasoning): $4×1.5 relative to the lowest price among the compared models
Kimi K2.5 (Reasoning): Best: $2.75

Context window

Kimi K2.6 (Non-reasoning): 256K
Kimi K2.5 (Reasoning): 256K

Reasoning

Kimi K2.6 (Non-reasoning): No
Kimi K2.5 (Reasoning): Yes

Open weights

Kimi K2.6 (Non-reasoning): Yes
Kimi K2.5 (Reasoning): Yes

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 K2.6 (Non-reasoning)23.6 · $1.71
Kimi K2.5 (Reasoning)23.5 · $1.14