Model Comparator

Compare up to four models using the same criteria.

JT-4.1 Flash 236B A21B (Non-reasoning)
China Mobile
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	JT-4.1 Flash 236B A21B (Non-reasoning) China Mobile	Kimi K2.6 (Reasoning) Moonshot AI
Intelligence	Best: 27.3	27
Coding	52.4	Best: 61.8
Agentic	—	20.5
Speed	—	52.8 t/s
TTFT	—	2.99 s
Input · $ / 1M tokens	—	$0.95
Output · $ / 1M tokens	—	$4
Context window	Best: 262K	256K
Reasoning	No	Yes
Open weights	No	Yes
Cost / task	—	$0.80

Intelligence

JT-4.1 Flash 236B A21B (Non-reasoning): Best: 27.3
Kimi K2.6 (Reasoning): 27

Coding

JT-4.1 Flash 236B A21B (Non-reasoning): 52.4
Kimi K2.6 (Reasoning): Best: 61.8

Agentic

JT-4.1 Flash 236B A21B (Non-reasoning): —
Kimi K2.6 (Reasoning): 20.5

Speed

JT-4.1 Flash 236B A21B (Non-reasoning): —
Kimi K2.6 (Reasoning): 52.8 t/s

TTFT

JT-4.1 Flash 236B A21B (Non-reasoning): —
Kimi K2.6 (Reasoning): 2.99 s

Input · $ / 1M tokens

JT-4.1 Flash 236B A21B (Non-reasoning): —
Kimi K2.6 (Reasoning): $0.95

Output · $ / 1M tokens

JT-4.1 Flash 236B A21B (Non-reasoning): —
Kimi K2.6 (Reasoning): $4

Context window

JT-4.1 Flash 236B A21B (Non-reasoning): Best: 262K
Kimi K2.6 (Reasoning): 256K

Reasoning

JT-4.1 Flash 236B A21B (Non-reasoning): No
Kimi K2.6 (Reasoning): Yes

Open weights

JT-4.1 Flash 236B A21B (Non-reasoning): No
Kimi K2.6 (Reasoning): Yes

Cost / task

JT-4.1 Flash 236B A21B (Non-reasoning): —
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.

Kimi K2.6 (Reasoning)27 · $0.80

Not plotted for lack of data on these axes: JT-4.1 Flash 236B A21B (Non-reasoning).