Model Comparator

Compare up to four models using the same criteria.

Kimi K3 (Max)
Moonshot AI
Step 3.5 Flash
StepFun

Differences only

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

Model Comparator
Metrics	Kimi K3 (Max) Moonshot AI	Step 3.5 Flash StepFun
Intelligence	Best: 17.4	17
Coding	72	—
Agentic	29.3	—
Cyber Index	41.3%	—
Speed	48.3 t/s	Best: 122 t/s
TTFT	3.81 s	Best: 3.28 s
Input · $ / 1M tokens	$3×30 relative to the lowest price among the compared models	Best: $0.10
Output · $ / 1M tokens	$15×50 relative to the lowest price among the compared models	Best: $0.30
Context window	1M	1M
Reasoning	Yes	Yes
Open weights	Yes	Yes
Cost / task	$2.00	—

Intelligence

Kimi K3 (Max): Best: 17.4
Step 3.5 Flash: 17

Coding

Kimi K3 (Max): 72
Step 3.5 Flash: —

Agentic

Kimi K3 (Max): 29.3
Step 3.5 Flash: —

Cyber Index

Kimi K3 (Max): 41.3%
Step 3.5 Flash: —

Speed

Kimi K3 (Max): 48.3 t/s
Step 3.5 Flash: Best: 122 t/s

TTFT

Kimi K3 (Max): 3.81 s
Step 3.5 Flash: Best: 3.28 s

Input · $ / 1M tokens

Kimi K3 (Max): $3×30 relative to the lowest price among the compared models
Step 3.5 Flash: Best: $0.10

Output · $ / 1M tokens

Kimi K3 (Max): $15×50 relative to the lowest price among the compared models
Step 3.5 Flash: Best: $0.30

Context window

Kimi K3 (Max): 1M
Step 3.5 Flash: 1M

Reasoning

Kimi K3 (Max): Yes
Step 3.5 Flash: Yes

Open weights

Kimi K3 (Max): Yes
Step 3.5 Flash: Yes

Cost / task

Kimi K3 (Max): $2.00
Step 3.5 Flash: —

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 · $6
Step 3.5 Flash17 · $0.15