Search for model performance across languages and benchmarks
Evaluate LLM over-refusal rates with OR-Bench
Calculate survival probability based on passenger details
Convert and upload model files for Stable Diffusion
Evaluate adversarial robustness using generative models
View and submit machine learning model evaluations
Request model evaluation on COCO val 2017 dataset
Persian Text Embedding Benchmark
Display benchmark results
Create and upload a Hugging Face model card
Display and filter leaderboard models
SolidityBench Leaderboard
Calculate VRAM requirements for LLM models
The Open Multilingual LLM Leaderboard is a tool designed for benchmarking and evaluating the performance of large language models (LLMs) across multiple languages and diverse benchmarks. It provides a comprehensive platform to compare model capabilities, identify strengths, and uncover limitations in multilingual contexts. This leaderboard is particularly useful for researchers, developers, and practitioners working on multilingual NLP tasks.
• Multilingual Support: Covers a wide range of languages, enabling cross-lingual comparisons.
• Diverse Benchmarks: Includes various benchmarking datasets and metrics tailored for multilingual evaluation.
• Model Comparison: Allows side-by-side comparison of different LLMs based on performance metrics.
• Detailed Metrics: Provides in-depth analysis, including accuracy, F1-scores, and other relevant performance indicators.
• Open Access: Easily accessible for researchers and developers to explore and analyze model performance.
• Real-Time Updates: Regularly updated with the latest models and benchmark results.
What languages are supported on the Open Multilingual LLM Leaderboard?
The leaderboard supports a wide range of languages, including but not limited to English, Spanish, French, Mandarin, Hindi, and Arabic. For the most up-to-date list, check the platform directly.
How often is the leaderboard updated?
The leaderboard is updated regularly, with new models and benchmarks added as they become available. Follow the platform for notifications on updates.
Is the Open Multilingual LLM Leaderboard free to use?
Yes, the platform is open access and free to use for researchers, developers, and the general public. However, some advanced features may require registration or subscription.
Can I submit my own model for evaluation?
Yes, the platform allows submissions of new models for benchmarking. Visit the submission guidelines section for more details.
How are the models ranked?
Models are ranked based on their performance across various benchmarks and metrics. The ranking is dynamically updated as new results are added.