Display benchmark results
Search for model performance across languages and benchmarks
Demo of the new, massively multilingual leaderboard
View and submit LLM benchmark evaluations
Calculate memory needed to train AI models
Benchmark AI models by comparison
Compare model weights and visualize differences
Download a TriplaneGaussian model checkpoint
Compare code model performance on benchmarks
Compare and rank LLMs using benchmark scores
Convert and upload model files for Stable Diffusion
Find recent high-liked Hugging Face models
Evaluate model predictions with TruLens
Redteaming Resistance Leaderboard is a model benchmarking tool designed to evaluate and compare the performance of AI models in resisting adversarial attacks. It provides a comprehensive platform to display benchmark results, enabling researchers and developers to assess the robustness of their models against various threat scenarios. The leaderboard serves as a centralized resource for identifying top-performing models and tracking progress in adversarial defense.
What models are included in the leaderboard?
The leaderboard features a diverse range of AI models, including state-of-the-art architectures designed for adversarial defense.
How often are the results updated?
Results are updated in real-time to ensure the latest advancements in model resistance are reflected.
Can I contribute my own model to the leaderboard?
Yes, submissions are welcome. Please refer to the platform's documentation for guidelines on model submission and evaluation criteria.