Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models818Deals30d270Policy30d79, 18 pendingSources1,159

Qwen3.8 Max Preview vs Step 5 Preview

Alibaba · released

Wins 2 of 6 areas

Agents · Images and charts

StepFun · released

Wins 2 of 6 areas

Reasoning · Long documents

The two are evenly matched.Qwen3.8 Max Preview is better at agents and images and charts; Step 5 Preview at reasoning and long documents.

Both rank among the ten best models we track in long documents.

Scores updated · 15 tests both models report · How we compare

Where each one wins

Tests won in each of the six areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.

Long documents rests on a single test.

What it costs

Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.

Qwen3.8 Max Preview$2.00 to read · $6.00 to write$8.00Price from Alibaba's own price page
Step 5 Preview$1.00 to read · $2.70 to write$3.70Price from Artificial Analysis

Step 5 Preview costs 54% less for the same work.

The biggest differences

The three tests each model wins by the widest margin. Scores are out of 100.

Where Qwen3.8 Max Preview pulls ahead

  • Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+14.2points aheadQwen3.8 Max Preview71.2Step 5 Preview57
  • Harder college exam questions with imagesMMMU-Pro+6.4points aheadQwen3.8 Max Preview82.8Step 5 Preview76.4
  • Complex command-line tasks across many fieldsTerminal-Bench 4.0+5.6points aheadQwen3.8 Max Preview38.9Step 5 Preview33.3

Where Step 5 Preview pulls ahead

  • Finds the root cause of IT system incidentsAA IT-Bench SRE+15.3points aheadStep 5 Preview55.6Qwen3.8 Max Preview40.3
  • Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+9.8points aheadStep 5 Preview41.5Qwen3.8 Max Preview31.7
  • Reasons across sets of long documentsAA-LCR+8points aheadStep 5 Preview88.3Qwen3.8 Max Preview80.3

Every test, side by side

All 15 tests both models report. The winning score is in its model's colour; marks a score checked independently.

CodingEven

Full coding ranking

AgentsQwen3.8 Max Preview
  • AA IT-Bench SREStep 5 Preview by 15.340.355.6+15.3
  • Terminal-Bench 4.0Qwen3.8 Max Preview by 5.638.933.3+5.6
  • AA ApexAgentsQwen3.8 Max Preview by 4.442.438+4.4
  • GDPValQwen3.8 Max Preview by 458.354.3+4

Full agents ranking

ReasoningStep 5 Preview

Full reasoning ranking

FactsEven

Full facts ranking

Images and chartsQwen3.8 Max Preview

Full images and charts ranking

Long documentsStep 5 Preview
  • AA-LCRStep 5 Preview by 880.388.3+8

Full long documents ranking

Other results2 tests, not counted

Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.

Questions people ask

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

Qwen3.8 Max Preview and Step 5 Preview each win two of the six areas where both have results. Qwen3.8 Max Preview wins agents and images and charts; Step 5 Preview wins reasoning and long documents. Step 5 Preview costs 54% less. They are level on coding and facts.

Which is better for coding?

Neither. They win 1 coding test each of the 2 both models report.

Which is cheaper?

Qwen3.8 Max Preview costs $2.00 per million input tokens and $6.00 per million output tokens; Step 5 Preview costs $1.00 and $2.70. That makes Step 5 Preview about 54% cheaper for the same work.

How do you compare the two?

We use the 15 benchmark tests both models have published scores on. The verdict counts the 13 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 2 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.