Zhoufutu Wen

FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning

IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs

TreePO: Enhancing Policy Efficacy and Inference Efficiency with Tree Modeling

DiscoX: Benchmarking Discourse-Level Translation in Expert Domains

Beyond Score: A Multi-Agent System to Discover Capability and Behavioral Weaknesses in LLMs

SciDA: Scientific Dynamic Assessor of LLMs

Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures

MME-CC: A Challenging Multi-Modal Evaluation Benchmark of Cognitive Capacity

First return, entropy-eliciting explore

CryptoX : Compositional Reasoning Evaluation of Large Language Models

COIG-Writer: A High-Quality Chinese Creative Writing with Thought Process Dataset

KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation