Model Comparator

Compare up to four models using the same criteria.

Claude 3.7 Sonnet (Reasoning)
Anthropic
Muse Glimmer (High)
Meta

Differences only

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

Model Comparator
Metrics	Claude 3.7 Sonnet (Reasoning) Anthropic	Muse Glimmer (High) Meta
Intelligence	Best: 17.7	17.5
Coding	36.4	Best: 49
Math	56.3	—
Agentic	—	8.5
Speed	—	124 t/s
TTFT	—	1.09 s
Input · $ / 1M tokens	—	$0.30
Output · $ / 1M tokens	—	$1.20
Context window	Best: 200K	131K
Reasoning	Yes	Yes
Open weights	No	Yes
Cost / task	—	$0.0535

Intelligence

Claude 3.7 Sonnet (Reasoning): Best: 17.7
Muse Glimmer (High): 17.5

Coding

Claude 3.7 Sonnet (Reasoning): 36.4
Muse Glimmer (High): Best: 49

Math

Claude 3.7 Sonnet (Reasoning): 56.3
Muse Glimmer (High): —

Agentic

Claude 3.7 Sonnet (Reasoning): —
Muse Glimmer (High): 8.5

Speed

Claude 3.7 Sonnet (Reasoning): —
Muse Glimmer (High): 124 t/s

TTFT

Claude 3.7 Sonnet (Reasoning): —
Muse Glimmer (High): 1.09 s

Input · $ / 1M tokens

Claude 3.7 Sonnet (Reasoning): —
Muse Glimmer (High): $0.30

Output · $ / 1M tokens

Claude 3.7 Sonnet (Reasoning): —
Muse Glimmer (High): $1.20

Context window

Claude 3.7 Sonnet (Reasoning): Best: 200K
Muse Glimmer (High): 131K

Reasoning

Claude 3.7 Sonnet (Reasoning): Yes
Muse Glimmer (High): Yes

Open weights

Claude 3.7 Sonnet (Reasoning): No
Muse Glimmer (High): Yes

Cost / task

Claude 3.7 Sonnet (Reasoning): —
Muse Glimmer (High): $0.0535

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 Glimmer (High)17.5 · $0.0535

Not plotted for lack of data on these axes: Claude 3.7 Sonnet (Reasoning).