https://arxiv.org/abs/2406.01574?utm_campaign=The%20Batch&utm_medium=email&_hsenc=p2ANqtz-_J-a1Me5M2qJj42YrpCiOpKZXedgkjMMd7JgRqZbTftAbo3LwzduWZ6BwqVyP0HweLkkZOftczGDWEwHqfOgX11pD_uNNLO8A4j70tw71f-jRecho&_hsmi=353823758&utm_content=353823758&utm_source=hs_email
Abstract page for arXiv paper 2406.01574: MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
mmlu prorobustchallengingmulti
https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/discussions/332
This PR adds community-provided evaluation results for the following benchmarks:
meta llamaadd communityinstruct