This repository contains the evaluation data presented in: OneThinker: All-in-one Reasoning Model for Image and Video

Code: https://github.com/tulerfeng/OneThinker

About OneThinker

We introduce OneThinker, an all-in-one multimodal reasoning generalist that is capable of thinking across a wide range of fundamental visual tasks within a single model.

We construct the large-scale OneThinker-600k multi-task training corpus and build OneThinker-SFT-340k with high-quality CoT annotations for cold-start SFT. Moreover, we propose EMA-GRPO, a new RL method that balances heterogeneous reward signals across diverse visual tasks, via simply tracking task-wise moving averages of reward std.

OneThinker demonstrates strong performance on 31 benchmarks across 10 fundamental vision tasks, while showing cross-task knowledge transfer and promising zero-shot generalization toward a unified multimodal reasoning generalist.