Model Comparator

Compare up to four models using the same criteria.

Claude 3.7 Sonnet (Reasoning)
Anthropic
Kimi K3 (Max)
Moonshot AI

Differences only

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

Model Comparator
Metrics	Claude 3.7 Sonnet (Reasoning) Anthropic	Kimi K3 (Max) Moonshot AI
Intelligence	Best: 17.7	17.4
Coding	36.4	Best: 72
Math	56.3	—
Agentic	—	29.3
Cyber Index	—	41.3%
Speed	—	48.3 t/s
TTFT	—	3.81 s
Input · $ / 1M tokens	—	$3
Output · $ / 1M tokens	—	$15
Context window	200K	Best: 1M
Reasoning	Yes	Yes
Open weights	No	Yes
Cost / task	—	$2.00

Intelligence

Claude 3.7 Sonnet (Reasoning): Best: 17.7
Kimi K3 (Max): 17.4

Coding

Claude 3.7 Sonnet (Reasoning): 36.4
Kimi K3 (Max): Best: 72

Math

Claude 3.7 Sonnet (Reasoning): 56.3
Kimi K3 (Max): —

Agentic

Claude 3.7 Sonnet (Reasoning): —
Kimi K3 (Max): 29.3

Cyber Index

Claude 3.7 Sonnet (Reasoning): —
Kimi K3 (Max): 41.3%

Speed

Claude 3.7 Sonnet (Reasoning): —
Kimi K3 (Max): 48.3 t/s

TTFT

Claude 3.7 Sonnet (Reasoning): —
Kimi K3 (Max): 3.81 s

Input · $ / 1M tokens

Claude 3.7 Sonnet (Reasoning): —
Kimi K3 (Max): $3

Output · $ / 1M tokens

Claude 3.7 Sonnet (Reasoning): —
Kimi K3 (Max): $15

Context window

Claude 3.7 Sonnet (Reasoning): 200K
Kimi K3 (Max): Best: 1M

Reasoning

Claude 3.7 Sonnet (Reasoning): Yes
Kimi K3 (Max): Yes

Open weights

Claude 3.7 Sonnet (Reasoning): No
Kimi K3 (Max): Yes

Cost / task

Claude 3.7 Sonnet (Reasoning): —
Kimi K3 (Max): $2.00

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 (Max)17.4 · $2.00

Not plotted for lack of data on these axes: Claude 3.7 Sonnet (Reasoning).