Model Comparator

Compare up to four models using the same criteria.

Qwen3 Next 80B A3B Thinking
Qwen
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	Qwen3 Next 80B A3B Thinking Qwen	Granite 4.2 8B IBM
Intelligence	Best: 11.2	11.1
Coding	17.4	Best: 22.4
Agentic	—	1.3
Speed	—	118 t/s
TTFT	—	0.85 s
Input · $ / 1M tokens	$0.15×2.5 relative to the lowest price among the compared models	Best: $0.060
Output · $ / 1M tokens	$1.20×4.8 relative to the lowest price among the compared models	Best: $0.25
Context window	Best: 262K	131K
Reasoning	Yes	Yes
Open weights	Yes	Yes
Cost / task	—	$0.0236

Intelligence

Qwen3 Next 80B A3B Thinking: Best: 11.2
Granite 4.2 8B: 11.1

Coding

Qwen3 Next 80B A3B Thinking: 17.4
Granite 4.2 8B: Best: 22.4

Agentic

Qwen3 Next 80B A3B Thinking: —
Granite 4.2 8B: 1.3

Speed

Qwen3 Next 80B A3B Thinking: —
Granite 4.2 8B: 118 t/s

TTFT

Qwen3 Next 80B A3B Thinking: —
Granite 4.2 8B: 0.85 s

Input · $ / 1M tokens

Qwen3 Next 80B A3B Thinking: $0.15×2.5 relative to the lowest price among the compared models
Granite 4.2 8B: Best: $0.060

Output · $ / 1M tokens

Qwen3 Next 80B A3B Thinking: $1.20×4.8 relative to the lowest price among the compared models
Granite 4.2 8B: Best: $0.25

Context window

Qwen3 Next 80B A3B Thinking: Best: 262K
Granite 4.2 8B: 131K

Reasoning

Qwen3 Next 80B A3B Thinking: Yes
Granite 4.2 8B: Yes

Open weights

Qwen3 Next 80B A3B Thinking: Yes
Granite 4.2 8B: Yes

Cost / task

Qwen3 Next 80B A3B Thinking: —
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.

Qwen3 Next 80B A3B Thinking11.2 · $0.413
Granite 4.2 8B11.1 · $0.107