AIME 2025

AIME 2025 Dataset Dataset Description This dataset contains problems from the American Invitational Mathematics Examination (AIME) 2025-I & II.

Papers using AIME 2025 (9)

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning2026Reflective Confidence: Correcting Reasoning Flaws via Online Self-Correction2025BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping2025BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping2025Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think2025Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier2025Not All Correct Answers Are Equal: Why Your Distillation Source Matters2025UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities2025DeepPrune: Parallel Scaling without Inter-trace Redundancy2025