Across
- 2. Recent findings
- 3. Problem challenge level
- 5. Consistency measuring tool
- 6. Math question
- 10. G-Pass@k
- 12. New discoveries
- 13. Tough math exam
- 15. LLM heroes
Down
- 1. Inconsistent performance
- 4. Reliable performance
- 7. Exam subject
- 8. Find solution
- 9. Correct solution
- 11. Large Language Models
- 14. LiveMathBench