RoboBench Benchmark for MLLM Robotics Evaluation
English multimodal test suite for checking how well vision-language models reason in robotics scenarios.
- Robotics
- Visual question answering
- English
Hugging Face datasets with plain-language descriptions: what's inside and what models to train on them. 4,788 in the catalog so far, with new ones added every hour.
Answered by Gemini 4 · the chat is kept only in this tab
English multimodal test suite for checking how well vision-language models reason in robotics scenarios.
Synthetic dataset from Stability AI and LAION with English handwritten text images for OCR and generation.
Large-scale set of 1 to 10 million examples alternating images, text, and actions for training embodied AI.
Combined corpus of 16 datasets with video, audio, and text for recognizing emotions, humor, and human state.
Official set of tasks from AtCoder contests for evaluating AI systems in algorithmic programming with scoring.
Light microscopy images and annotations for 3D and 2D neuron reconstruction.
A massive collection of Chinese image-text pairs totaling approximately 7.9 TB for image-to-text tasks.
Classic corpus of ~3.3 million image-text pairs collected from HTML Alt-text tags.
2,323 scientific charts from arXiv papers to test multimodal model ability to understand complex visualizations.
Infographic charts with text annotations for visual understanding and generation tasks.
A Google Research dataset with multi-temporal aerospace image pairs and questions about terrain changes.
Visual math problems with images and text for evaluating VLMs.
A large-scale image-text dataset with camera geometry for spatial AI.
Image-instruction pairs for training visual assistants in English.
Image-caption pairs from arXiv research publications with metadata for multimodal models.
15M English image-text pairs for training and evaluating open multimodal models.
An English and Chinese image-text dataset for deep evaluation of Text-to-Image models.
A multimodal benchmark of 18,000 samples to assist in CAD program generation and understanding.
4.8M multimodal GPT-4-Vision video descriptions for LVLM and text-to-video models.
Problems from countries and competitions with images and text for QA and solution generation.
Updated benchmark with English videos and annotations for comprehensive evaluation of video models.
Image and text connections from Wikipedia across many languages for training and evaluating multimodal retrieval.
1K to 10K test examples with images and questions to evaluate vision capabilities in multimodal models.
~3.3M web images with alt-text captions for image-to-text training.