Multiple modes of explanations for any STEM topic in a single view that helps with learning a concept thoroughly. Gives ELI5, diagrams, examples, real world usages, more references. Allows to dig deeper into any concept, right click on any section and keep expanding your explanations.You can try the sample questions without any login. Free for use.
> is it open-source? No, it isn't open source rn - it's most vibe coded so not in the best shape to be open source.
> which LLM are you using? LLM wise - it's configurable, I keep switching between Gemini 2.5 Pro, o3 and fine tuned 4.1. I switch models between different actions as well. The initial explanation vs getting more details/chatting. Generally I have found o3 to be better one with generating explanations e2e.
Raw results: - 75 total questions - 67 correct answers - 6 questions couldn't be processed (required diagram input - not supported yet) - 2 incorrect - 97% accuracy on processable questions, 89% overall
The JEE covers advanced physics, chemistry, and mathematics at a level that traditionally requires years of intensive preparation.
The two failures were revealing:
Physics optics problem: The LLM made a sign error when differentiating the mirror equation for image acceleration. My extensive formatting rules could have also led to this which I want to look further into.
Chemical kinetics problem: Failed on a numerical simplification step. The official solution uses a neat trick of replacing e^-23.031 with e^(ln 10 × 10) to make the arithmetic manageable. The LLM computed the raw exponential instead and accumulated rounding errors.
Both were numerical answer questions (no multiple choice options to guide toward the right approach).
I think it's too early to comment about any kind of reliability but I find the results very interesting.
Will be working on more JEE papers soon and report back with culmulative stats with more questions.
AI can't solve math, physics, chemistry questions completely but AI can definitely help you understand them better. Having used NotebookLM and being a fan of Veritasium, 3B1B, SciShow for learning, I realise how powerful multi-modal learning is. Allowing students multiple hooks into a concept can help them understand the concept much better. This is what my project does for competitive exam...