Model Comparator

Compare up to four models using the same criteria.

Celeris-1
Celeris
Phi-4 Mini Instruct
Microsoft

Differences only

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

Model Comparator
Metrics	Celeris-1 Celeris	Phi-4 Mini Instruct Microsoft
Intelligence	6.3	6.3
Coding	Best: 14.4	3.8
Math	—	6.7
Agentic	0.7	—
Speed	Best: 1,663 t/s	45.6 t/s
TTFT	Best: 0.55 s	0.88 s
Input · $ / 1M tokens	$0.20×2.7 relative to the lowest price among the compared models	Best: $0.075
Output · $ / 1M tokens	$0.70×2.3 relative to the lowest price among the compared models	Best: $0.30
Context window	1M	1M
Reasoning	No	No
Open weights	No	Yes
Cost / task	$0.0502	—

Intelligence

Celeris-1: 6.3
Phi-4 Mini Instruct: 6.3

Coding

Celeris-1: Best: 14.4
Phi-4 Mini Instruct: 3.8

Math

Celeris-1: —
Phi-4 Mini Instruct: 6.7

Agentic

Celeris-1: 0.7
Phi-4 Mini Instruct: —

Speed

Celeris-1: Best: 1,663 t/s
Phi-4 Mini Instruct: 45.6 t/s

TTFT

Celeris-1: Best: 0.55 s
Phi-4 Mini Instruct: 0.88 s

Input · $ / 1M tokens

Celeris-1: $0.20×2.7 relative to the lowest price among the compared models
Phi-4 Mini Instruct: Best: $0.075

Output · $ / 1M tokens

Celeris-1: $0.70×2.3 relative to the lowest price among the compared models
Phi-4 Mini Instruct: Best: $0.30

Context window

Celeris-1: 1M
Phi-4 Mini Instruct: 1M

Reasoning

Celeris-1: No
Phi-4 Mini Instruct: No

Open weights

Celeris-1: No
Phi-4 Mini Instruct: Yes

Cost / task

Celeris-1: $0.0502
Phi-4 Mini Instruct: —

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.

Celeris-16.3 · $0.325
Phi-4 Mini Instruct6.3 · $0.131