🚀10B parameters, 200B+ performance！
Introducing STEP3-VL-10B : our open-source SOTA vision language model.
🥊 At just 10B, it redefines efficiency by matching or exceeding the capabilities of 100B/200B-scale models.
SOTA Performance :
✅STEM/Multimodal: Outperforms GLM-4.6V (106B-A12B) and Qwen3-VL (235B-A22B) on MMMU, MathVision, MathVerse,etc.
✅Math: Near-perfect scores on AIME 24/25, achieving elite-level reasoning.
✅2D/3D Spatial Understanding: Beating same-scale models on BLINK/CVBench/OmniSpatial.
✅Coding:Dominates LiveCodeBench in real-world dynamic programming.
Key Breakthroughs:
🔹 1.2T token full-parameter pre-training.
🔹 1,400+ RL iterations for superior reasoning.
🔹 Innovative PaCoRe tech for dynamic compute allocation.
💡We prove that scale isn't everything.
With high-quality targeted data and systematic post-training, a 10B model can go toe-to-toe with the industry's largest giants."
📱Complex AI reasoning is now accessible for every device.
Check out the Base & Thinking versions on HuggingFace now!
Homepage：https://t.co/xn82bwwTzD
Paper：https://t.co/flxKXRbCBW
HuggingFace：https://t.co/6YV5wF6iai
ModelScope：
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
pretraining — The first, biggest phase of building a model: training it on enormous amounts of text so it learns language, facts, and reasoning in general.
multimodal — A model that works with more than text — reading images, audio, or video, and sometimes generating them too.
Why it matters
A 10B open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition → vision LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition → reporting results at or above GLM-4.6V and Qwen3-VL on MMMU and MathVision puts strong multimodalA model that works with more than text — reading images, audio, or video, and sometimes generating them too.Full definition → reasoning within reach of single-device deployment, with weights and a paper available to verify.
article👏🏻Congratulations！Step3-VL-10B was selected for HuggingFace Daily Papers…
postStep-Audio-R1.1 opens weights for a speech model that reasons in real time
