Model Comparator

Compare up to four models using the same criteria.

Phi-4 Mini Instruct
Microsoft
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	Phi-4 Mini Instruct Microsoft	Muse Glimmer (High) Meta
Intelligence	6.3	6.3
Coding	3.8	Best: 49
Math	6.7	—
Agentic	—	8.5
Speed	45.1 t/s	Best: 120 t/s
TTFT	Best: 0.86 s	1.17 s
Input · $ / 1M tokens	Best: $0.075	$0.30×4 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $0.30	$1.20×4 relative to the lowest price among the compared models
Context window	Best: 1M	131K
Reasoning	No	Yes
Open weights	Yes	Yes
Cost / task	—	$0.161

Intelligence

Phi-4 Mini Instruct: 6.3
Muse Glimmer (High): 6.3

Coding

Phi-4 Mini Instruct: 3.8
Muse Glimmer (High): Best: 49

Math

Phi-4 Mini Instruct: 6.7
Muse Glimmer (High): —

Agentic

Phi-4 Mini Instruct: —
Muse Glimmer (High): 8.5

Speed

Phi-4 Mini Instruct: 45.1 t/s
Muse Glimmer (High): Best: 120 t/s

TTFT

Phi-4 Mini Instruct: Best: 0.86 s
Muse Glimmer (High): 1.17 s

Input · $ / 1M tokens

Phi-4 Mini Instruct: Best: $0.075
Muse Glimmer (High): $0.30×4 relative to the lowest price among the compared models

Output · $ / 1M tokens

Phi-4 Mini Instruct: Best: $0.30
Muse Glimmer (High): $1.20×4 relative to the lowest price among the compared models

Context window

Phi-4 Mini Instruct: Best: 1M
Muse Glimmer (High): 131K

Reasoning

Phi-4 Mini Instruct: No
Muse Glimmer (High): Yes

Open weights

Phi-4 Mini Instruct: Yes
Muse Glimmer (High): Yes

Cost / task

Phi-4 Mini Instruct: —
Muse Glimmer (High): $0.161

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.

Phi-4 Mini Instruct6.3 · $0.131
Muse Glimmer (High)6.3 · $0.525