Model Comparator

Compare up to four models using the same criteria.

Qwen3.5 27B (Non-reasoning)
Alibaba
K-EXAONE 2.0
LG AI Research

Differences only

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

Model Comparator
Metrics	Qwen3.5 27B (Non-reasoning) Alibaba	K-EXAONE 2.0 LG AI Research
Intelligence	19.4	Best: 19.7
Coding	—	40.6
Speed	81.7 t/s	—
TTFT	5.63 s	—
Input · $ / 1M tokens	$0.30	—
Output · $ / 1M tokens	$2.40	—
Context window	Best: 1M	262K
Reasoning	No	Yes
Open weights	Yes	Yes

Intelligence

Qwen3.5 27B (Non-reasoning): 19.4
K-EXAONE 2.0: Best: 19.7

Coding

Qwen3.5 27B (Non-reasoning): —
K-EXAONE 2.0: 40.6

Speed

Qwen3.5 27B (Non-reasoning): 81.7 t/s
K-EXAONE 2.0: —

TTFT

Qwen3.5 27B (Non-reasoning): 5.63 s
K-EXAONE 2.0: —

Input · $ / 1M tokens

Qwen3.5 27B (Non-reasoning): $0.30
K-EXAONE 2.0: —

Output · $ / 1M tokens

Qwen3.5 27B (Non-reasoning): $2.40
K-EXAONE 2.0: —

Context window

Qwen3.5 27B (Non-reasoning): Best: 1M
K-EXAONE 2.0: 262K

Reasoning

Qwen3.5 27B (Non-reasoning): No
K-EXAONE 2.0: Yes

Open weights

Qwen3.5 27B (Non-reasoning): Yes
K-EXAONE 2.0: 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.

Qwen3.5 27B (Non-reasoning)19.4 · $0.825

Not plotted for lack of data on these axes: K-EXAONE 2.0.