Model Comparator

Compare up to four models using the same criteria.

Qwen3.5 35B A3B (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	Qwen3.5 35B A3B (Reasoning) Alibaba	Step 3.7 Flash StepFun
Intelligence	19.3	Best: 19.5
Coding	37	Best: 39.6
Speed	147 t/s	Best: 185 t/s
TTFT	Best: 2.08 s	2.53 s
Input · $ / 1M tokens	$0.25×1.3 relative to the lowest price among the compared models	Best: $0.20
Output · $ / 1M tokens	$2×1.7 relative to the lowest price among the compared models	Best: $1.15
Context window	262K	262K
Reasoning	Yes	Yes
Open weights	Yes	Yes

Intelligence

Qwen3.5 35B A3B (Reasoning): 19.3
Step 3.7 Flash: Best: 19.5

Coding

Qwen3.5 35B A3B (Reasoning): 37
Step 3.7 Flash: Best: 39.6

Speed

Qwen3.5 35B A3B (Reasoning): 147 t/s
Step 3.7 Flash: Best: 185 t/s

TTFT

Qwen3.5 35B A3B (Reasoning): Best: 2.08 s
Step 3.7 Flash: 2.53 s

Input · $ / 1M tokens

Qwen3.5 35B A3B (Reasoning): $0.25×1.3 relative to the lowest price among the compared models
Step 3.7 Flash: Best: $0.20

Output · $ / 1M tokens

Qwen3.5 35B A3B (Reasoning): $2×1.7 relative to the lowest price among the compared models
Step 3.7 Flash: Best: $1.15

Context window

Qwen3.5 35B A3B (Reasoning): 262K
Step 3.7 Flash: 262K

Reasoning

Qwen3.5 35B A3B (Reasoning): Yes
Step 3.7 Flash: Yes

Open weights

Qwen3.5 35B A3B (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.

Qwen3.5 35B A3B (Reasoning)19.3 · $0.688
Step 3.7 Flash19.5 · $0.438