Model Comparator

Compare up to four models using the same criteria.

Claude Opus 5 (Xhigh)
Anthropic
Muse Wonder Full (Max)
Meta

Differences only

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

Model Comparator
Metrics	Claude Opus 5 (Xhigh) Anthropic	Muse Wonder Full (Max) Meta
Intelligence	49.7	Best: 50.1
Coding	77	—
Agentic	55.6	—
Speed	50.1 t/s	—
TTFT	34.7 s	—
Input · $ / 1M tokens	$5	—
Output · $ / 1M tokens	$25	—
Context window	1M	1M
Reasoning	Yes	Yes
Open weights	No	No
Cost / task	$4.88	—
Availability	—	Not publicly available

Intelligence

Claude Opus 5 (Xhigh): 49.7
Muse Wonder Full (Max): Best: 50.1

Coding

Claude Opus 5 (Xhigh): 77
Muse Wonder Full (Max): —

Agentic

Claude Opus 5 (Xhigh): 55.6
Muse Wonder Full (Max): —

Speed

Claude Opus 5 (Xhigh): 50.1 t/s
Muse Wonder Full (Max): —

TTFT

Claude Opus 5 (Xhigh): 34.7 s
Muse Wonder Full (Max): —

Input · $ / 1M tokens

Claude Opus 5 (Xhigh): $5
Muse Wonder Full (Max): —

Output · $ / 1M tokens

Claude Opus 5 (Xhigh): $25
Muse Wonder Full (Max): —

Context window

Claude Opus 5 (Xhigh): 1M
Muse Wonder Full (Max): 1M

Reasoning

Claude Opus 5 (Xhigh): Yes
Muse Wonder Full (Max): Yes

Open weights

Claude Opus 5 (Xhigh): No
Muse Wonder Full (Max): No

Cost / task

Claude Opus 5 (Xhigh): $4.88
Muse Wonder Full (Max): —

Availability

Claude Opus 5 (Xhigh): —
Muse Wonder Full (Max): Not publicly available

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.

Claude Opus 5 (Xhigh)49.7 · $4.88

Not plotted for lack of data on these axes: Muse Wonder Full (Max).