Qwen3.8 Max 0902 vs Step 5 Preview compared

Qwen3.8 Max 0902 leads the intelligence index 33.7 to 28.5. Step 5 Preview costs 52% less on blended price. Compare price, speed, latency and a clear verdict.

Metric	Qwen3.8 Max (0902)	Step 5 Preview
Intelligence Index	33.7	28.5
Input price (per 1M tokens)	$2.00	$1.00
Output price (per 1M tokens)	$6.00	$2.70
Output speed (tokens/s)	38	151
Time to first token	3.2s	0.91s
Release date	2026-09-02	2026-09-18

Metric

Qwen3.8 Max (0902)

Step 5 Preview

Intelligence Index

33.7

28.5

Input price (per 1M tokens)

$2.00

$1.00

Output price (per 1M tokens)

$6.00

$2.70

Output speed (tokens/s)

151

Time to first token

3.2s

0.91s

Release date

2026-09-02

2026-09-18

Qwen3.8 Max (0902) from Alibaba and Step 5 Preview from StepFun are both tracked in Franklin AI's benchmark catalogue. Step 5 Preview streams output at about 151 tokens per second, 4 times the rate of Qwen3.8 Max 0902. All numbers are the catalogue's recorded values; nobody ran either model by hand for this page.

Waiting time

Measured output speed is 38 tokens per second for Qwen3.8 Max 0902 and 151 tokens per second for Step 5 Preview. On long outputs, that is a real advantage for Step 5 Preview. Before any text appears, Qwen3.8 Max 0902 takes 3.2 seconds and Step 5 Preview 0.91 seconds. In an interactive app, Step 5 Preview will feel noticeably more responsive.

Put together, a 2,000-token answer would take about 56 seconds from Qwen3.8 Max 0902 and 14 seconds from Step 5 Preview, counting the first-token wait.

Qwen3.8 Max 0902 leads on the intelligence index

Qwen3.8 Max 0902 comes out ahead on the intelligence index, 33.7 to 28.5. A lead of this size is hard to dismiss as noise. In relative terms, Qwen3.8 Max 0902 scores 18% higher.

Across the 109 active models with an intelligence score in the catalogue, Qwen3.8 Max 0902 ranks 44th and Step 5 Preview ranks 61st.

Neither model has a separate coding or math index recorded yet, so those narrower comparisons will have to wait for more data.

When they came out

Qwen3.8 Max 0902 came first, on September 2, 2026; Step 5 Preview followed on September 18, 2026. That is close enough to count them as the same generation.

Cost: Step 5 Preview is cheaper

The list prices are $2.00 in and $6.00 out for Qwen3.8 Max 0902, and $1.00 in and $2.70 out for Step 5 Preview, per million tokens. That makes Step 5 Preview's output 55% cheaper.

For a sample workload of 1 million input tokens and 200,000 output tokens, Qwen3.8 Max 0902 would cost $3.20 and Step 5 Preview $1.54, a difference of $1.66. For a month of coding-assistant traffic at 30 million input and 3 million output tokens, Step 5 Preview would come in 51% lower: $78.00 for Qwen3.8 Max 0902 against $38.10 for Step 5 Preview.

Is the price in proportion?

Per point of intelligence index, Qwen3.8 Max 0902 costs $0.089 of blended price per million tokens and Step 5 Preview $0.050. So Qwen3.8 Max 0902 buys its higher score at a premium, while Step 5 Preview is the value pick, paying 44% less per point.

Common questions about Qwen3.8 Max 0902 and Step 5 Preview

Is Step 5 Preview better than Qwen3.8 Max 0902?

It depends on what you need: Qwen3.8 Max 0902 scores higher on the intelligence index, 33.7 to 28.5; Step 5 Preview is 52% cheaper on blended price; and Step 5 Preview streams output 4 times as fast.

Which is newer, Qwen3.8 Max 0902 or Step 5 Preview?

Step 5 Preview is newer. It was released on September 18, 2026, 16 days after Qwen3.8 Max 0902 (September 2, 2026).

Where do these numbers come from?

The figures are the recorded benchmark, price and speed data in Franklin AI's model catalogue. This page is written from that data automatically; neither model was tested by hand for it.

How much do Qwen3.8 Max 0902 and Step 5 Preview cost?

Step 5 Preview is cheaper on a blended basis. Qwen3.8 Max 0902 lists $2.00 per million input tokens and $6.00 per million output tokens; Step 5 Preview lists $1.00 and $2.70. For 1 million input and 200,000 output tokens that is $3.20 against $1.54.

Does Qwen3.8 Max 0902 respond faster than Step 5 Preview?

Step 5 Preview generates output faster, at 151 tokens per second against 38 tokens per second. Step 5 Preview reaches its first token sooner (0.91 seconds against 3.2 seconds).

Final whistle

In one line: Step 5 Preview has more going for it here, but Qwen3.8 Max 0902 is not without an argument. Pick Qwen3.8 Max 0902 if you need the higher overall score (33.7 against 28.5). Pick Step 5 Preview if long outputs need to finish quickly and cost matters ($2.70 against $6.00 per million output tokens).

Where the numbers come from

The scores, speed and prices in this comparison come from independent third-party model evaluations that Franklin AI syncs each day, and the article was written from a snapshot of them. For the latest results, open the Qwen3.8 Max (0902) and Step 5 Preview pages. The AI Benchmark methodology explains how that data is collected and shown.