Step-R1-V-Mini
A new multimodal reasoning model that supports image and text input, text output, and has high-precision image perception and complex reasoning capabilities.
PremiumNewProductProductivityMultimodal reasoningimage recognition
Step-R1-V-Mini is a new multimodal reasoning model launched by Jieyue Xingchen. It supports image and text input and text output, and has good instruction following and general capabilities. The model has been technically optimized for reasoning performance in multimodal collaborative scenarios. It employs multimodal joint reinforcement learning and a training method that makes full use of multimodal synthetic data, effectively improving the model's ability to handle complex chain processing in image space. Step-R1-V-Mini has performed brilliantly in several public leaderboards, particularly ranking first domestically in the MathVision visual reasoning leaderboard, demonstrating its excellent performance in visual reasoning, mathematical logic, and code. The model has been officially launched on the Jieyue AI web page and provides API interfaces on the Jieyue Xingchen open platform for developers and researchers to experience and use.
Step-R1-V-Mini Visit Over Time
Monthly Visits
46568
Bounce Rate
42.93%
Page per Visit
3.9
Visit Duration
00:03:29