evaluation-task · Source-linked discovery
LiveCodeBench-Pro: Competitive Programming Benchmark
Evaluates LLMs on competitive programming problems using a specialized Docker sandbox (LightCPVerifier) to execute and judge C++ code submissions against hidden test cases with time and memory constraints.
OriginZihan Zheng, Zerui Cheng, Zeyu Shen et al.TopicsGeneral capabilityStatusimported
Can support
Not independently assessed by FronteraEval yet.
Cannot support by itself
No inference beyond the upstream source should be made until the protocol is reviewed.