Tag: LLM benchmarking
Browse our exclusive articles!
IndustryCode: Multi-Domain Benchmark for Code Generation
IndustryCode offers a comprehensive benchmark to evaluate LLMs on multi-domain industrial code generation across diverse programming languages.
Benchmarking Educational LLMs for Gender Bias in Feedback
Explore how educational LLMs exhibit gender bias in feedback and learn methods to benchmark and ensure fairness in AI-driven teaching tools.
LocationReasoner: Benchmarking LLMs for Real-World Site Selection
Evaluate large language models' reasoning on real-world site selection with LocationReasoner, a benchmark for spatial and logistic decision-making tasks.
Benchmarking LLMs for Repository-Level Code QA
Explore how LLMs perform on repository-level question answering with StackRepoQA, highlighting challenges and advancements in multi-file code comprehension...