Running on CPU Upgrade Featured 3.41k The Smol Training Playbook 📚 3.41k The secrets to building world-class LLMs
Sleeping Agents 3 VideoEval-Pro Leaderboard 🥇 3 A more robust benchmark for long video understanding.
Running on CPU Upgrade Agents 29 Gaia2 Agents Evaluation Leaderboard 🐠 29 Explore AI model performance on the Gaia2 benchmark
Running on Zero Agents Featured 935 Qwen Image 🖼 935 Generate detailed images from text prompts with AI enhancement
Running 5 41 LLMs Evaluated Locally on 19 Benchmarks ⚡ 5 41 open-source LLMs benchmarked locally on 19 tasks.
Running 95 Bringing paper to life: A modern template for scientific writing 📝 95 Create publish‑ready scientific papers instantly