Model Comparator

Compare up to four models using the same criteria.

2 models compared

  1. Celeris-1

    Celeris

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

Intelligence

Phi-4 Mini Instruct
6.3
Celeris-1
6.3

Coding

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

Math

Phi-4 Mini Instruct
6.7
Celeris-1
—

Agentic

Phi-4 Mini Instruct
—
Celeris-1
0.7

Speed

Phi-4 Mini Instruct
46.1 t/s
Celeris-1
Best: 1,459 t/s

TTFT

Phi-4 Mini Instruct
0.82 s
Celeris-1
Best: 0.61 s

Input · $ / 1M tokens

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

Output · $ / 1M tokens

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

Context window

Phi-4 Mini Instruct
128K
Celeris-1
Best: 131K

Reasoning

Phi-4 Mini Instruct
No
Celeris-1
No

Open weights

Phi-4 Mini Instruct
Yes
Celeris-1
No

Cost / task

Phi-4 Mini Instruct
—
Celeris-1
$0.0502

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.

Intelligence Indexmost efficient ↗Price / 1M tokens
  • Phi-4 Mini Instruct6.3 · $0.131
  • Celeris-16.3 · $0.325

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy