Model Comparator

Compare up to four models using the same criteria.

Nova 2.0 Pro Preview (Non-reasoning)
Amazon
North Mini Code
Cohere

Differences only

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

Model Comparator
Metrics	Nova 2.0 Pro Preview (Non-reasoning) Amazon	North Mini Code Cohere
Intelligence	Best: 10	9.9
Coding	20.9	Best: 36.5
Math	30.7	—
Agentic	—	1.1
Speed	Best: 106 t/s	82 t/s
TTFT	1.03 s	Best: 0.46 s
Input · $ / 1M tokens	$1.38	—
Output · $ / 1M tokens	$11	—
Context window	256K	256K
Reasoning	No	Yes
Open weights	No	Yes
Cost / task	—	$0

Intelligence

Nova 2.0 Pro Preview (Non-reasoning): Best: 10
North Mini Code: 9.9

Coding

Nova 2.0 Pro Preview (Non-reasoning): 20.9
North Mini Code: Best: 36.5

Math

Nova 2.0 Pro Preview (Non-reasoning): 30.7
North Mini Code: —

Agentic

Nova 2.0 Pro Preview (Non-reasoning): —
North Mini Code: 1.1

Speed

Nova 2.0 Pro Preview (Non-reasoning): Best: 106 t/s
North Mini Code: 82 t/s

TTFT

Nova 2.0 Pro Preview (Non-reasoning): 1.03 s
North Mini Code: Best: 0.46 s

Input · $ / 1M tokens

Nova 2.0 Pro Preview (Non-reasoning): $1.38
North Mini Code: —

Output · $ / 1M tokens

Nova 2.0 Pro Preview (Non-reasoning): $11
North Mini Code: —

Context window

Nova 2.0 Pro Preview (Non-reasoning): 256K
North Mini Code: 256K

Reasoning

Nova 2.0 Pro Preview (Non-reasoning): No
North Mini Code: Yes

Open weights

Nova 2.0 Pro Preview (Non-reasoning): No
North Mini Code: Yes

Cost / task

Nova 2.0 Pro Preview (Non-reasoning): —
North Mini Code: $0

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.

Nova 2.0 Pro Preview (Non-reasoning)10 · 106 t/s
North Mini Code9.9 · 82 t/s