Model Comparator

Compare up to four models using the same criteria.

Nova 2.0 Omni (Low)
Amazon
Granite 4.2 8B
IBM

Differences only

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

Model Comparator
Metrics	Nova 2.0 Omni (Low) Amazon	Granite 4.2 8B IBM
Intelligence	11.1	11.1
Coding	—	22.4
Math	56	—
Agentic	—	1.3
Speed	—	118 t/s
TTFT	—	0.85 s
Input · $ / 1M tokens	$0.30×5 relative to the lowest price among the compared models	Best: $0.060
Output · $ / 1M tokens	$2.50×10 relative to the lowest price among the compared models	Best: $0.25
Context window	Best: 1M	131K
Reasoning	Yes	Yes
Open weights	No	Yes
Cost / task	—	$0.0236

Intelligence

Nova 2.0 Omni (Low): 11.1
Granite 4.2 8B: 11.1

Coding

Nova 2.0 Omni (Low): —
Granite 4.2 8B: 22.4

Math

Nova 2.0 Omni (Low): 56
Granite 4.2 8B: —

Agentic

Nova 2.0 Omni (Low): —
Granite 4.2 8B: 1.3

Speed

Nova 2.0 Omni (Low): —
Granite 4.2 8B: 118 t/s

TTFT

Nova 2.0 Omni (Low): —
Granite 4.2 8B: 0.85 s

Input · $ / 1M tokens

Nova 2.0 Omni (Low): $0.30×5 relative to the lowest price among the compared models
Granite 4.2 8B: Best: $0.060

Output · $ / 1M tokens

Nova 2.0 Omni (Low): $2.50×10 relative to the lowest price among the compared models
Granite 4.2 8B: Best: $0.25

Context window

Nova 2.0 Omni (Low): Best: 1M
Granite 4.2 8B: 131K

Reasoning

Nova 2.0 Omni (Low): Yes
Granite 4.2 8B: Yes

Open weights

Nova 2.0 Omni (Low): No
Granite 4.2 8B: Yes

Cost / task

Nova 2.0 Omni (Low): —
Granite 4.2 8B: $0.0236

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 Omni (Low)11.1 · $0.85
Granite 4.2 8B11.1 · $0.107