Model Comparator

Compare up to four models using the same criteria.

Qwen3.6 27B (Non-reasoning)
Alibaba
Step 3.7 Flash
StepFun

Differences only

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

Model Comparator
Metrics	Qwen3.6 27B (Non-reasoning) Alibaba	Step 3.7 Flash StepFun
Intelligence	Best: 19.8	19.5
Coding	Best: 46.6	39.6
Speed	55.5 t/s	Best: 190 t/s
TTFT	3.69 s	Best: 2.53 s
Input · $ / 1M tokens	$0.60×3 relative to the lowest price among the compared models	Best: $0.20
Output · $ / 1M tokens	$3.60×3.1 relative to the lowest price among the compared models	Best: $1.15
Context window	262K	262K
Reasoning	No	Yes
Open weights	Yes	Yes

Intelligence

Qwen3.6 27B (Non-reasoning): Best: 19.8
Step 3.7 Flash: 19.5

Coding

Qwen3.6 27B (Non-reasoning): Best: 46.6
Step 3.7 Flash: 39.6

Speed

Qwen3.6 27B (Non-reasoning): 55.5 t/s
Step 3.7 Flash: Best: 190 t/s

TTFT

Qwen3.6 27B (Non-reasoning): 3.69 s
Step 3.7 Flash: Best: 2.53 s

Input · $ / 1M tokens

Qwen3.6 27B (Non-reasoning): $0.60×3 relative to the lowest price among the compared models
Step 3.7 Flash: Best: $0.20

Output · $ / 1M tokens

Qwen3.6 27B (Non-reasoning): $3.60×3.1 relative to the lowest price among the compared models
Step 3.7 Flash: Best: $1.15

Context window

Qwen3.6 27B (Non-reasoning): 262K
Step 3.7 Flash: 262K

Reasoning

Qwen3.6 27B (Non-reasoning): No
Step 3.7 Flash: Yes

Open weights

Qwen3.6 27B (Non-reasoning): Yes
Step 3.7 Flash: 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.

Qwen3.6 27B (Non-reasoning)19.8 · $1.35
Step 3.7 Flash19.5 · $0.438