Step 3.7 Flash
StepFun · 1 configuration
Intelligence19.5
Input / 1M$0.20
Output / 1M$1.15
Context262.1K
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
Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
19.5 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
80.9 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
21.4 %SciCodeCode generation for scientific research problems.
43.9 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
39.3 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
98.5 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
67.3 %MMMU-ProMultimodal understanding of academic problems that include images.
75.3 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
25.8 %Specifications from the catalog
Inputtext, image, video
Outputtext
Tool callingYes
Structured outputYes
Speed182.8 tok/s
First token2.57 s
Maximum output230.4K
Catalog listing date2026-05-28