Model Comparator

Compare up to four models using the same criteria.

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 0709 (Reasoning) China Mobile	Muse Spark 1.1 (Xhigh) Meta
Intelligence	Best: 33.9	33.7
Coding	52.4	Best: 71.3
Agentic	—	25.8
Speed	—	187 t/s
TTFT	—	13.8 s
Input · $ / 1M tokens	—	$1.25
Output · $ / 1M tokens	—	$4.25
Context window	262K	Best: 1.05M
Reasoning	Yes	Yes
Open weights	No	No
Cost / task	—	$1.13

Intelligence

JT-4.1 Flash 236B A21B 0709 (Reasoning): Best: 33.9
Muse Spark 1.1 (Xhigh): 33.7

Coding

JT-4.1 Flash 236B A21B 0709 (Reasoning): 52.4
Muse Spark 1.1 (Xhigh): Best: 71.3

Agentic

JT-4.1 Flash 236B A21B 0709 (Reasoning): —
Muse Spark 1.1 (Xhigh): 25.8

Speed

JT-4.1 Flash 236B A21B 0709 (Reasoning): —
Muse Spark 1.1 (Xhigh): 187 t/s

TTFT

JT-4.1 Flash 236B A21B 0709 (Reasoning): —
Muse Spark 1.1 (Xhigh): 13.8 s

Input · $ / 1M tokens

JT-4.1 Flash 236B A21B 0709 (Reasoning): —
Muse Spark 1.1 (Xhigh): $1.25

Output · $ / 1M tokens

JT-4.1 Flash 236B A21B 0709 (Reasoning): —
Muse Spark 1.1 (Xhigh): $4.25

Context window

JT-4.1 Flash 236B A21B 0709 (Reasoning): 262K
Muse Spark 1.1 (Xhigh): Best: 1.05M

Reasoning

JT-4.1 Flash 236B A21B 0709 (Reasoning): Yes
Muse Spark 1.1 (Xhigh): Yes

Open weights

JT-4.1 Flash 236B A21B 0709 (Reasoning): No
Muse Spark 1.1 (Xhigh): No

Cost / task

JT-4.1 Flash 236B A21B 0709 (Reasoning): —
Muse Spark 1.1 (Xhigh): $1.13

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.

Muse Spark 1.1 (Xhigh)33.7 · $1.13

Not plotted for lack of data on these axes: JT-4.1 Flash 236B A21B 0709 (Reasoning).