AIQ PRO

aiqtech

AI & ML interests

None yet

Recent Activity

liked a Space 1 day ago
openfree/Korean-Exam-Leaderboard
reacted to openfree's post with โž• 1 day ago
Korean Exam Leaderboard: LLMs vs Civil Service and Professional Qualification Exams ๐Ÿ“ https://huggingface.co/spaces/openfree/Korean-Exam-Leaderboard ## ๐Ÿ“Š What is this leaderboard? This leaderboard evaluates the performance of various AI models on 22 Korean civil service and professional qualification exams. All scores are converted to a 100-point scale to show how well different LLMs can solve actual Korean civil service and professional qualification tests! ## ๐Ÿ† Current Top Performers - **OpenAI/GPT-o1**: Bar Exam 52.5 points ๐Ÿฅ‡ - **OpenAI/GPT-4.5**: Bar Exam 49.33 points ๐Ÿฅˆ - **OpenAI/GPT-4o**: Bar Exam 49.11 points ๐Ÿฅ‰ - **deepseek-ai/DeepSeek-R1**: Bar Exam 47.33 points ## ๐Ÿ“‹ Exams Being Evaluated The leaderboard includes various Korean civil service and professional qualification exams: - Korean Bar Exam - Senior Civil Service Grade 5 - Judicial Service Grade 5 - National Assembly Grade 5 - Judicial Scrivener - Police Executive Candidate - And more exams! ## ๐Ÿค– Models Being Evaluated We are testing a variety of models: - OpenAI: GPT-o1, GPT-o3-mini, GPT-4.5, GPT-4o - Anthropic: Claude 3.7 Sonnet - Google: Gemini 2.0 Flash/PRO/Flash Thinking - Meta: Llama 3.3 70B Instruct, Llama 3.2 90B Vision - DeepSeek: DeepSeek-R1 - Qwen: QwQ-32B, Qwen2.5 Coder - Mistral: Mistral-Small-3.1-24B - NVIDIA models: NVIDIA Nemotron variant models - And many more! ## ๐Ÿ” Why This Matters Korean civil service exams are known for their high difficulty and comprehensive knowledge assessment. These exams test deep knowledge across legal, administrative, and public service domains. Success in these exams demonstrates not just language understanding but also domain expertise and reasoning ability. ## ๐Ÿงช Evaluation Methodology ๐Ÿ”œ Future Plans We are continuously expanding our test coverage across all 22 exam categories. We will keep updating the scores marked "TBD" so please stay tuned!
reacted to openfree's post with ๐Ÿ˜Ž 1 day ago
Korean Exam Leaderboard: LLMs vs Civil Service and Professional Qualification Exams ๐Ÿ“ https://huggingface.co/spaces/openfree/Korean-Exam-Leaderboard ## ๐Ÿ“Š What is this leaderboard? This leaderboard evaluates the performance of various AI models on 22 Korean civil service and professional qualification exams. All scores are converted to a 100-point scale to show how well different LLMs can solve actual Korean civil service and professional qualification tests! ## ๐Ÿ† Current Top Performers - **OpenAI/GPT-o1**: Bar Exam 52.5 points ๐Ÿฅ‡ - **OpenAI/GPT-4.5**: Bar Exam 49.33 points ๐Ÿฅˆ - **OpenAI/GPT-4o**: Bar Exam 49.11 points ๐Ÿฅ‰ - **deepseek-ai/DeepSeek-R1**: Bar Exam 47.33 points ## ๐Ÿ“‹ Exams Being Evaluated The leaderboard includes various Korean civil service and professional qualification exams: - Korean Bar Exam - Senior Civil Service Grade 5 - Judicial Service Grade 5 - National Assembly Grade 5 - Judicial Scrivener - Police Executive Candidate - And more exams! ## ๐Ÿค– Models Being Evaluated We are testing a variety of models: - OpenAI: GPT-o1, GPT-o3-mini, GPT-4.5, GPT-4o - Anthropic: Claude 3.7 Sonnet - Google: Gemini 2.0 Flash/PRO/Flash Thinking - Meta: Llama 3.3 70B Instruct, Llama 3.2 90B Vision - DeepSeek: DeepSeek-R1 - Qwen: QwQ-32B, Qwen2.5 Coder - Mistral: Mistral-Small-3.1-24B - NVIDIA models: NVIDIA Nemotron variant models - And many more! ## ๐Ÿ” Why This Matters Korean civil service exams are known for their high difficulty and comprehensive knowledge assessment. These exams test deep knowledge across legal, administrative, and public service domains. Success in these exams demonstrates not just language understanding but also domain expertise and reasoning ability. ## ๐Ÿงช Evaluation Methodology ๐Ÿ”œ Future Plans We are continuously expanding our test coverage across all 22 exam categories. We will keep updating the scores marked "TBD" so please stay tuned!
View all activity

Organizations

KAISAR's profile picture

Posts 1

view post
Post
3527
๐ŸŽจ SORA 3D: Create 3D Models from Text and Images
Hey there! Today I'm excited to share 'SORA 3D', a project that generates 3D models from text prompts or images.
โœจ Key Features

3D generation from text/image input
Multilingual prompt support
Automatic GLB conversion
Real-time 3D preview
Mesh optimization & texture quality control

๐Ÿš€ How to Use

Enter text or upload image
Adjust generation settings (optional)
Click 'Generate 3D'
Extract and download GLB file

๐Ÿ›  Tech Stack

Hugging Face Transformers
PyTorch
Gradio
TRELLIS image-to-3D conversion
FLUX image generation

๐Ÿ’ก Use Cases

Game asset creation
Metaverse content
Product prototyping
Educational 3D models

LINK: ginipick/SORA-3D

Try the demo and let me know what you think! ๐Ÿ˜Š
#AI #3DGeneration #MachineLearning #HuggingFace #ComputerVision