Hello HF,
We are the authors of CHI-Bench actava/chi-bench · Datasets at Hugging Face , we would like to have our dataset integrated as a huggingface benchmark dataset and hope to get help from the team. The benchmark itself is run on harbor as the eval harness. We hope that HF team can help us preparing the PRs to the model repo and whitelist the benchmark by the end. Should you have any question, feel free to reach out to me.
Best,