ProgramBench Tests If LLMs Can Rebuild Code
A new benchmark called ProgramBench challenges language models to reconstruct entire programs from specifications, revea…
11 articles about 'code generation'
A new benchmark called ProgramBench challenges language models to reconstruct entire programs from specifications, revea…
Mistral AI unveils Codestral 2.0, a specialized code generation model targeting enterprise developers with improved accu…
Mistral AI unveils Codestral Mamba, a state space model delivering ultra-fast code generation with theoretically infinit…
Mistral AI launches Codestral 2.0, its most powerful code generation model yet, targeting enterprise developers with imp…
Mistral AI releases Codestral 2, its most powerful code generation model yet, targeting enterprise development teams wit…
French AI startup Mistral AI launches Codestral 2, delivering major improvements in multilingual code generation and age…
Proven prompt engineering techniques can boost Claude code generation quality by reducing errors and improving structure…
Mistral AI releases Codestral 2, a specialized coding model promising major performance gains for developers across mult…
LG AI Research launches EXAONE 4.0 with enhanced code generation and mathematical reasoning, challenging global LLM lead…
Carnegie Mellon researchers develop a reinforcement learning framework that lets code generation models iteratively impr…
Mistral AI unveils Codestral Large, a powerful code generation model designed to compete in the enterprise AI coding mar…