StepFun·Step

STEP3-VL-10B

A compact multimodal open model in the Step 3 line at about 10B scale, focused on visual perception, complex reasoning, and human-centric alignment.

CurrentLanguageReasoningMultimodalOpen weights

MODEL NUMBER338

Specifications

Only published specifications are shown.

A compact multimodal open model in the Step 3 line at about 10B scale, focused on visual perception, complex reasoning, and human-centric alignment.

STEP3-VL-10B brings Step’s visual reasoning to a more deployable scale and uses parallel coordinated reasoning to scale test-time compute.

ReasoningVision

2026-01-14Open weights

STEP3-VL-10B open model suite released.

Select a card to view the related model.

Suggest a correction

Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.

Model ID: step3-vl-10b
Page: https://llmlineage.com/en/models/step3-vl-10b
Field:
Proposed value:
Primary source URL:
Reason: