Model Comparator

Compare up to four models using the same criteria.

DeepSeek V3.1 Terminus (Non-reasoning)
DeepSeek
Apriel-v1.5-15B-Thinker
ServiceNow

Differences only

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

Model Comparator
Metrics	DeepSeek V3.1 Terminus (Non-reasoning) DeepSeek	Apriel-v1.5-15B-Thinker ServiceNow
Intelligence	Best: 13.9	13.8
Coding	43.5	—
Math	53.7	Best: 87.5
Agentic	6.8	—
Speed	40.8 t/s	—
TTFT	1.15 s	—
Input · $ / 1M tokens	$0.27	—
Output · $ / 1M tokens	$1	—
Context window	128K	128K
Reasoning	No	Yes
Open weights	Yes	Yes

Intelligence

DeepSeek V3.1 Terminus (Non-reasoning): Best: 13.9
Apriel-v1.5-15B-Thinker: 13.8

Coding

DeepSeek V3.1 Terminus (Non-reasoning): 43.5
Apriel-v1.5-15B-Thinker: —

Math

DeepSeek V3.1 Terminus (Non-reasoning): 53.7
Apriel-v1.5-15B-Thinker: Best: 87.5

Agentic

DeepSeek V3.1 Terminus (Non-reasoning): 6.8
Apriel-v1.5-15B-Thinker: —

Speed

DeepSeek V3.1 Terminus (Non-reasoning): 40.8 t/s
Apriel-v1.5-15B-Thinker: —

TTFT

DeepSeek V3.1 Terminus (Non-reasoning): 1.15 s
Apriel-v1.5-15B-Thinker: —

Input · $ / 1M tokens

DeepSeek V3.1 Terminus (Non-reasoning): $0.27
Apriel-v1.5-15B-Thinker: —

Output · $ / 1M tokens

DeepSeek V3.1 Terminus (Non-reasoning): $1
Apriel-v1.5-15B-Thinker: —

Context window

DeepSeek V3.1 Terminus (Non-reasoning): 128K
Apriel-v1.5-15B-Thinker: 128K

Reasoning

DeepSeek V3.1 Terminus (Non-reasoning): No
Apriel-v1.5-15B-Thinker: Yes

Open weights

DeepSeek V3.1 Terminus (Non-reasoning): Yes
Apriel-v1.5-15B-Thinker: Yes

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.

DeepSeek V3.1 Terminus (Non-reasoning)13.9 · $0.453

Not plotted for lack of data on these axes: Apriel-v1.5-15B-Thinker.