← all datasets

AIME-25

Emerging

3papers using it

2026first seen

'AIME'25' is a benchmark dataset used to evaluate the performance of models on mathematical tasks.

🔎 Find this dataset

Papers using AIME-25 (3)

SePO: Self-Evolving Prompt Agent for System Prompt Optimization2026

Empirical-MCTS: Continuous Agent Evolution via Dual-Experience Monte Carlo Tree Search2026

SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models2026

AIME-25 dataset — papers, benchmarks & downloads · AI Agents