Model Comparator

Compare up to four models using the same criteria.

Claude Fable 5 (batch)
Anthropic
Muse Spark 1.3 (Max)
Meta

Differences only

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

Model Comparator
Metrics	Claude Fable 5 (batch) Anthropic	Muse Spark 1.3 (Max) Meta
Intelligence	Best: 49.6	48.1
Coding	Best: 76.5	75.8
Agentic	50.7	Best: 55.5
Speed	—	114 t/s
TTFT	—	79.6 s
Input · $ / 1M tokens	—	$1.25
Output · $ / 1M tokens	—	$4.25
Context window	1M	1M
Reasoning	Yes	Yes
Open weights	—	No
Cost / task	—	$1.60

Intelligence

Claude Fable 5 (batch): Best: 49.6
Muse Spark 1.3 (Max): 48.1

Coding

Claude Fable 5 (batch): Best: 76.5
Muse Spark 1.3 (Max): 75.8

Agentic

Claude Fable 5 (batch): 50.7
Muse Spark 1.3 (Max): Best: 55.5

Speed

Claude Fable 5 (batch): —
Muse Spark 1.3 (Max): 114 t/s

TTFT

Claude Fable 5 (batch): —
Muse Spark 1.3 (Max): 79.6 s

Input · $ / 1M tokens

Claude Fable 5 (batch): —
Muse Spark 1.3 (Max): $1.25

Output · $ / 1M tokens

Claude Fable 5 (batch): —
Muse Spark 1.3 (Max): $4.25

Context window

Claude Fable 5 (batch): 1M
Muse Spark 1.3 (Max): 1M

Reasoning

Claude Fable 5 (batch): Yes
Muse Spark 1.3 (Max): Yes

Open weights

Claude Fable 5 (batch): —
Muse Spark 1.3 (Max): No

Cost / task

Claude Fable 5 (batch): —
Muse Spark 1.3 (Max): $1.60

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 1.3 (Max)48.1 · $1.60

Not plotted for lack of data on these axes: Claude Fable 5 (batch).