OlympiadBench

'OlympiadBench' is a benchmark used to evaluate complex reasoning capabilities of large language models (LLMs).

Papers using OlympiadBench (7)

Transformation-Augmented GRPO for Enhancing Exploration in Reasoning of Large Language Models2026LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding2026Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation2025Pairwise RM: Perform Best-of-N Sampling with Knockout Tournament2025SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization2025MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision2025Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models2025