Details

Publisher

Hunyuan Team, Tencent

Domain

Research & Learning

Category

Papers & Research

Type Group

Research & Papers

Best For

Research

Skill Level

Intermediate

Access

Free

Topic

A comprehensive, large-scale code generation benchmark comprising 3,920 carefully curated problems, featuring balanced distribution across 20 programming languages. This benchmark is characterized by its high difficulty levels, practical relevance, and linguistic diversity.

Related in Papers & Research

• Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM AgentsTianshi Xu, Huifeng Wen, Meng Li
• Awesome Code as Agent Harness PapersYennNing
• A Survey of Context Engineering for Large Language ModelsLingrui Mei et al.
• Language-Induced Priors for Domain AdaptationQiyuan Chen, Jiayu Zhou, Raed Al Kontar
• Contexting as Recommendation: Evolutionary Collaborative Filtering for Context EngineeringJiachen Zhu et al.
• 2025 AI Agent Index: Safety Features of Deployed Agentic Systems (arXiv:2602.17753)Stanford HAI / Independent Authors