Step 5 Preview
StepFun · 1 configuration
Intelligence43.7
Input / 1M$1.00
Output / 1M$2.70
Context1M
Tariff: StepFun · Source: artificial-analysis · USD per million tokens
Thinking configuration
What does more thinking buy you?
Compare this model’s measured thinking configurations.
Scroll the chart ↔ · tap a point for details
Efficient frontier: best measured score at each cost1 measured configurations · 0 without both values
Selected: thinking thinking · Click a point to switch configuration
StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
43.7 pointsHumanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
46.5 %SciCodeCode generation for scientific research problems.
58.9 %MMMU-ProMultimodal understanding of academic problems that include images.
76.4 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
41.5 %Specifications from the catalog
Inputtext, image, video
Outputtext
Tool callingYes
Structured outputYes
Speed85.4 tok/s
First token3.02 s
Maximum output131.1K
Catalog listing date2026-09-16