Evaluate and submit AI model results for Frugal AI Challenge
Track, rank and evaluate open LLMs and chatbots
Display and filter leaderboard models
Export Hugging Face models to ONNX
Measure over-refusal in LLMs using OR-Bench
Create and upload a Hugging Face model card
View NSQL Scores for Models
Text-To-Speech (TTS) Evaluation using objective metrics.
Compare and rank LLMs using benchmark scores
Visualize model performance on function calling tasks
View and compare language model evaluations
Calculate memory usage for LLM models
Convert Stable Diffusion checkpoint to Diffusers and open a PR
Submission Portal is a unified platform designed to evaluate and submit AI model results for the Frugal AI Challenge. It provides a seamless interface for researchers and developers to showcase their model's performance, ensuring standardization and comparability across submissions.
• Result Submission: Easily upload your model's results for evaluation. • Benchmarking: Compare your model's performance against industry standards and other submissions. • Result Visualization: Access detailed metrics and graphs to analyze your model's strengths and weaknesses. • Data Security: Your submissions are protected with robust security measures. • User-Friendly Interface: Intuitive design ensures a smooth experience for all users.
What file formats are supported for submission?
The portal supports CSV, JSON, and ZIP formats. Ensure your files are properly formatted before submission.
How long does the evaluation process take?
Evaluations are typically completed within 24-48 hours, depending on the complexity of your submission.
Can I edit my submission after uploading?
No, submissions are final once uploaded. Ensure all details are accurate before submitting.