Model Comparator

Compare up to four models using the same criteria.

Qwen3 8B (Reasoning)
Alibaba
Exaone 4.0 1.2B (Non-reasoning)
LG AI Research

Differences only

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

Model Comparator
Metrics	Qwen3 8B (Reasoning) Alibaba	Exaone 4.0 1.2B (Non-reasoning) LG AI Research
Intelligence	5.2	5.2
Coding	9	—
Math	19	Best: 24
Agentic	0.8	—
Speed	43.1 t/s	—
TTFT	3.89 s	—
Input · $ / 1M tokens	$0.18	—
Output · $ / 1M tokens	$2.10	—
Context window	Best: 131K	64K
Reasoning	Yes	No
Open weights	Yes	Yes

Intelligence

Qwen3 8B (Reasoning): 5.2
Exaone 4.0 1.2B (Non-reasoning): 5.2

Coding

Qwen3 8B (Reasoning): 9
Exaone 4.0 1.2B (Non-reasoning): —

Math

Qwen3 8B (Reasoning): 19
Exaone 4.0 1.2B (Non-reasoning): Best: 24

Agentic

Qwen3 8B (Reasoning): 0.8
Exaone 4.0 1.2B (Non-reasoning): —

Speed

Qwen3 8B (Reasoning): 43.1 t/s
Exaone 4.0 1.2B (Non-reasoning): —

TTFT

Qwen3 8B (Reasoning): 3.89 s
Exaone 4.0 1.2B (Non-reasoning): —

Input · $ / 1M tokens

Qwen3 8B (Reasoning): $0.18
Exaone 4.0 1.2B (Non-reasoning): —

Output · $ / 1M tokens

Qwen3 8B (Reasoning): $2.10
Exaone 4.0 1.2B (Non-reasoning): —

Context window

Qwen3 8B (Reasoning): Best: 131K
Exaone 4.0 1.2B (Non-reasoning): 64K

Reasoning

Qwen3 8B (Reasoning): Yes
Exaone 4.0 1.2B (Non-reasoning): No

Open weights

Qwen3 8B (Reasoning): Yes
Exaone 4.0 1.2B (Non-reasoning): 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.

Qwen3 8B (Reasoning)5.2 · $0.66

Not plotted for lack of data on these axes: Exaone 4.0 1.2B (Non-reasoning).