Model Comparator

Compare up to four models using the same criteria.

JT-4.1 Flash 236B A21B (Reasoning)
China Mobile
Qwen3.8 27B (Xhigh)
Alibaba

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 (Reasoning) China Mobile	Qwen3.8 27B (Xhigh) Alibaba
Intelligence	Best: 33.9	33.7
Coding	52.4	Best: 68.1
Agentic	—	45.8
Cyber Index	—	12.7%
Speed	—	41.2 t/s
TTFT	—	3.93 s
Input · $ / 1M tokens	—	$0.50
Output · $ / 1M tokens	—	$3
Context window	Best: 262K	256K
Reasoning	Yes	Yes
Open weights	No	No
Cost / task	—	$1.01

Intelligence

JT-4.1 Flash 236B A21B (Reasoning): Best: 33.9
Qwen3.8 27B (Xhigh): 33.7

Coding

JT-4.1 Flash 236B A21B (Reasoning): 52.4
Qwen3.8 27B (Xhigh): Best: 68.1

Agentic

JT-4.1 Flash 236B A21B (Reasoning): —
Qwen3.8 27B (Xhigh): 45.8

Cyber Index

JT-4.1 Flash 236B A21B (Reasoning): —
Qwen3.8 27B (Xhigh): 12.7%

Speed

JT-4.1 Flash 236B A21B (Reasoning): —
Qwen3.8 27B (Xhigh): 41.2 t/s

TTFT

JT-4.1 Flash 236B A21B (Reasoning): —
Qwen3.8 27B (Xhigh): 3.93 s

Input · $ / 1M tokens

JT-4.1 Flash 236B A21B (Reasoning): —
Qwen3.8 27B (Xhigh): $0.50

Output · $ / 1M tokens

JT-4.1 Flash 236B A21B (Reasoning): —
Qwen3.8 27B (Xhigh): $3

Context window

JT-4.1 Flash 236B A21B (Reasoning): Best: 262K
Qwen3.8 27B (Xhigh): 256K

Reasoning

JT-4.1 Flash 236B A21B (Reasoning): Yes
Qwen3.8 27B (Xhigh): Yes

Open weights

JT-4.1 Flash 236B A21B (Reasoning): No
Qwen3.8 27B (Xhigh): No

Cost / task

JT-4.1 Flash 236B A21B (Reasoning): —
Qwen3.8 27B (Xhigh): $1.01

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.

Qwen3.8 27B (Xhigh)33.7 · $1.01

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