datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
navitrace
NaviTrace
🏠 Project
📄 Paper
💻 Code
🏆 Leaderboard
NaviTrace is a novel VQA benchmark for VLMs that evaluates models on their embodiment-specific understanding of navigation across challenging real-world scenarios.
Key Features
✏️ Core Task: Given a real-world image in first-person perspective, a language instruction, and an embodiment type, models should predict… See the full description on the dataset page: https://huggingface.co/datasets/leggedrobotics/navitrace.mmlu
Dataset Card for MMLU
Dataset Summary
Measuring Massive Multitask Language Understanding by Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt (ICLR 2021).
This is a massive multitask test consisting of multiple-choice questions from various branches of knowledge. The test spans subjects in the humanities, social sciences, hard sciences, and other areas that are important for some people to learn. This covers 57 tasks… See the full description on the dataset page: https://huggingface.co/datasets/navitrix/mmlu.