Model Comparator

Compare up to four models using the same criteria.

Granite 4.2 30B
IBM
Qwen3 235B A22B Thinking 2507
Qwen

Differences only

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

Model Comparator
Metrics	Granite 4.2 30B IBM	Qwen3 235B A22B Thinking 2507 Qwen
Intelligence	12.7	12.7
Coding	Best: 29.9	22.1
Agentic	Best: 3.5	1.3
Speed	76.1 t/s	—
TTFT	0.9 s	—
Input · $ / 1M tokens	Best: $0.16	$0.45×2.8 relative to the lowest price among the compared models
Output · $ / 1M tokens	Best: $0.65	$3.50×5.4 relative to the lowest price among the compared models
Context window	Best: 131K	128K
Reasoning	Yes	Yes
Open weights	Yes	Yes
Cost / task	$0.0717	—

Intelligence

Granite 4.2 30B: 12.7
Qwen3 235B A22B Thinking 2507: 12.7

Coding

Granite 4.2 30B: Best: 29.9
Qwen3 235B A22B Thinking 2507: 22.1

Agentic

Granite 4.2 30B: Best: 3.5
Qwen3 235B A22B Thinking 2507: 1.3

Speed

Granite 4.2 30B: 76.1 t/s
Qwen3 235B A22B Thinking 2507: —

TTFT

Granite 4.2 30B: 0.9 s
Qwen3 235B A22B Thinking 2507: —

Input · $ / 1M tokens

Granite 4.2 30B: Best: $0.16
Qwen3 235B A22B Thinking 2507: $0.45×2.8 relative to the lowest price among the compared models

Output · $ / 1M tokens

Granite 4.2 30B: Best: $0.65
Qwen3 235B A22B Thinking 2507: $3.50×5.4 relative to the lowest price among the compared models

Context window

Granite 4.2 30B: Best: 131K
Qwen3 235B A22B Thinking 2507: 128K

Reasoning

Granite 4.2 30B: Yes
Qwen3 235B A22B Thinking 2507: Yes

Open weights

Granite 4.2 30B: Yes
Qwen3 235B A22B Thinking 2507: Yes

Cost / task

Granite 4.2 30B: $0.0717
Qwen3 235B A22B Thinking 2507: —

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.

Granite 4.2 30B12.7 · $0.282
Qwen3 235B A22B Thinking 250712.7 · $1.21