A comprehensive, fully-categorized analysis of 952 General Awareness (GK/GS) questions from the SSC CGL Tier 1 examination. Every question is classified by subject and sub-topic, with the full question text, all four options, and correct answers (extracted via LLM where available).
Distribution of all 952 questions across major subjects. Click any subject to dive deeper.
Total count of questions in each major subject area
Relative weight of each subject in the SSC CGL General Awareness section
Click any subject card to view detailed sub-topic breakdown and all questions
Ancient, Medieval, Modern Indian History & World History — 25 sub-topics from Indus Valley to Independence
Physical, Indian & World Geography — 11 sub-topics including rivers, climate, agriculture, industries
Constitution, Parliament, Judiciary, New Criminal Laws & Governance — 15 sub-topics
Indian Economy, Banking, Budget, Inflation & International Trade — 8 sub-topics
Physics, Chemistry & Biology — 12 sub-topics covering all major science areas
Books, Sports, Awards, Festivals, Dance (separate), Music (separate), Architecture, Space — 18 granular sub-topics
Recent Events, Schemes, Sports, Awards, Rankings — 8 sub-topics for 2024-25 events
Questions that could not be auto-categorized
Major data quality improvements
Re-parsed OCR text to recover missing options. Fixed 359 questions that had incomplete options by re-extracting from the raw OCR with a smarter parser.
Used z-ai chat LLM to re-extract clean options for questions where OCR was too garbled. LLM also provides the correct answer + explanation.
Questions with fewer than 4 options now show a red warning box, so you know exactly which questions need verification. No more silent bad data.
756 of 952 questions have all 4 options properly extracted. To get 100%, run the GitHub Actions Gemini OCR workflow with your own Gemini API key (works in US region).