OpenDCAI/Omni-Edu-9B
Omni-Edu-9B by OpenDCAI is a 9-billion parameter multimodal language model, fine-tuned from Qwen3.5-9B-Base with a 32,768-token context length. It is specifically designed for K–12 learning and teaching, integrating subject competence, curriculum grounding, diagnostic reasoning, and pedagogical scaffolding. This model excels at educational tasks, providing targeted feedback and adapting instructional support for students and teachers.
Loading preview...
OmniEdu-9B: Open Foundation Model for K–12 Learning and Teaching
OmniEdu-9B is a 9-billion parameter multimodal model developed by OpenDCAI, fine-tuned from Qwen3.5-9B-Base, specifically designed to support K–12 education. It integrates subject knowledge, curriculum understanding, learner diagnosis, and instructional support, making it a valuable tool for educational research and teacher-assistance applications. The model was trained with a 32,768-token sequence length on a mixture of 69,999 instruction examples, including 60,951 education-specific examples.
Key Capabilities
- Subject Competence: Solves K–12 problems across various subjects and input formats.
- Curriculum Grounding: Links questions, concepts, and solutions to curriculum standards and prerequisites.
- Diagnostic Reasoning: Identifies misconceptions, missing prerequisites, and gaps in learner understanding.
- Pedagogical Action & Scaffolding: Provides targeted feedback, asks guiding questions, explains concepts, and adapts instructional support.
Good for
- Educational Research: Prototyping and evaluating AI applications in K–12 learning.
- Teacher-Assistance Tools: Generating activity plans, diagnosing student misconceptions, and providing guided tutoring.
- Learning-Support Prototypes: Developing interactive educational experiences that adapt to individual learner needs.
OmniEdu-9B demonstrates strong performance on educational benchmarks, including K12-Bench (55.46% EM, 73.68% F1), MathFish (83.70% Acc.), and GAOKAO-Bench (93.66% Full), as detailed in the accompanying paper.