Model Comparator

Compare up to four models using the same criteria.

K-EXAONE (Non-reasoning)
LG AI Research
Qwen3 Next 80B A3B (Reasoning)
Alibaba

Differences only

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

Model Comparator
Metrics	K-EXAONE (Non-reasoning) LG AI Research	Qwen3 Next 80B A3B (Reasoning) Alibaba
Intelligence	11.2	11.2
Coding	—	17.4
Math	44	Best: 84.3
Speed	—	163 t/s
TTFT	—	0.71 s
Input · $ / 1M tokens	—	$0.15
Output · $ / 1M tokens	—	$1.20
Context window	Best: 2.02M	262K
Reasoning	No	Yes
Open weights	Yes	Yes

Intelligence

K-EXAONE (Non-reasoning): 11.2
Qwen3 Next 80B A3B (Reasoning): 11.2

Coding

K-EXAONE (Non-reasoning): —
Qwen3 Next 80B A3B (Reasoning): 17.4

Math

K-EXAONE (Non-reasoning): 44
Qwen3 Next 80B A3B (Reasoning): Best: 84.3

Speed

K-EXAONE (Non-reasoning): —
Qwen3 Next 80B A3B (Reasoning): 163 t/s

TTFT

K-EXAONE (Non-reasoning): —
Qwen3 Next 80B A3B (Reasoning): 0.71 s

Input · $ / 1M tokens

K-EXAONE (Non-reasoning): —
Qwen3 Next 80B A3B (Reasoning): $0.15

Output · $ / 1M tokens

K-EXAONE (Non-reasoning): —
Qwen3 Next 80B A3B (Reasoning): $1.20

Context window

K-EXAONE (Non-reasoning): Best: 2.02M
Qwen3 Next 80B A3B (Reasoning): 262K

Reasoning

K-EXAONE (Non-reasoning): No
Qwen3 Next 80B A3B (Reasoning): Yes

Open weights

K-EXAONE (Non-reasoning): Yes
Qwen3 Next 80B A3B (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 Next 80B A3B (Reasoning)11.2 · $0.412

Not plotted for lack of data on these axes: K-EXAONE (Non-reasoning).