2025
LiveBench: A Challenging, Contamination-Limited LLM Benchmark
ICLR 2025spotlight
Test set contamination, wherein test data from a benchmark ends up in a newer model's training set, is a well-documented obstacle for fair LLM evaluation and can quickly render benchmarks obsolete. To mitigate this, many recent benchmarks crowdsource new prompts and evaluations from human or LLM jud…