Papers with Code Datasets — Score 43.0 AI-092-nodate-model-datase-34acf393 Full article OpenDevin: An Open Platform for AI Software Developers as Generalist Agents
Papers with Code Datasets — Score 30.0 AI-092-nodate-model-datase-998651e9 Full article Vision Pretraining for Dense Spatial Perception
Papers with Code Datasets — Score 32.0 AI-092-nodate-model-datase-26fe6306 Full article SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Papers with Code Datasets — Score 43.0 AI-092-nodate-model-datase-5860ed44 Full article TradingAgents: Multi-Agents LLM Financial Trading Framework
Papers with Code Datasets — Score 28.0 AI-092-nodate-model-datase-e59e3817 Full article Continuous Audio Language Models
Papers with Code Datasets — Score 27.0 AI-092-nodate-model-datase-0c3c0e6b Full article AutoDev: Automated AI-Driven Development
Papers with Code Datasets — Score 30.0 AI-092-nodate-model-datase-9f3ef2a2 Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
Papers with Code Datasets — Score 25.0 AI-092-nodate-model-datase-4f12077c Full article Inference Providers
OpenReview — Score 7.0 AI-071-nodate-research-pap-fa4ebcfb IEEE ICRA 2026 Workshop Embodied AI and Telepresence
OpenReview — Score 12.0 AI-071-nodate-research-pap-f21c0eb7 IEEE RoboSoft 2026 Workshop Reproducibility Soft Robotics
OpenReview — Score 12.0 AI-071-nodate-research-pap-d32949b1 IEEE ICRA 2026 Workshop Planetary Robotics
OpenReview — Score 12.0 AI-071-nodate-research-pap-2f13d828 Full article ACM CHI 2026 Workshop Human-Agent Collaboration
OpenReview — Score 16.0 AI-071-nodate-research-pap-a7182044 Full article AIAgents4Qual 2026 Conference
OpenReview — Score 5.0 AI-071-nodate-research-pap-84df0431 Full article KDD 2026 AI4Sciences Track February
Ollama Library — Score 33.0 AI-099-nodate-model-datase-f130487f Full article codellama A large language model that can use text prompts to generate and discuss code. 7b 13b 34b 70b 5.8M Pulls 199 Tags Updated 1 year ago
Ollama Library — Score 38.0 AI-099-nodate-model-datase-d1b5c8c6 Full article qwen2 Qwen2 is a new series of large language models from Alibaba group tools 0.5b 1.5b 7b 72b 6M Pulls 97 Tags Updated 1 year ago
Ollama Library — Score 35.0 AI-099-nodate-model-datase-5ba0c268 Full article glm-ocr GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture. vision tools 6.1M Pulls 3 Tags Updated 5 months ago
Ollama Library — Score 43.0 AI-099-nodate-model-datase-1c581f94 Full article qwen3-coder Alibaba's performant long context models for agentic and coding tasks. tools cloud 30b 480b 7.2M Pulls 10 Tags Updated 9 months ago
Ollama Library — Score 33.0 AI-099-nodate-model-datase-feb8a4a4 Full article llama2 Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters. 7b 13b 70b 7.2M Pulls 102 Tags Updated 2 years ago
Ollama Library — Score 33.0 AI-099-nodate-model-datase-31685e9b Full article qwen Qwen 1.5 is a series of large language models by Alibaba Cloud spanning from 0.5B to 110B parameters 0.5b 1.8b 4b 7b 14b 32b 72b 110b 7.2M Pulls 379 Tags Updated 2 years ago
Ollama Library — Score 41.0 AI-099-nodate-model-datase-c2500bd7 Full article gemma Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1 2b 7b 7.2M Pulls 102 Tags Updated 2 years ago
Ollama Library — Score 32.0 AI-099-nodate-model-datase-54d7feab Full article phi4 Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft. 14b 7.6M Pulls 5 Tags Updated 1 year ago
Ollama Library — Score 54.0 AI-099-nodate-model-datase-aab04aa5 Full article gpt-oss OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. tools thinking cloud 20b 120b 10.8M Pulls 5 Tags Updated 9 months ago
Ollama Library — Score 35.0 AI-099-nodate-model-datase-b235ce3a Full article mxbai-embed-large State-of-the-art large embedding model from mixedbread.ai embedding 335m 12.4M Pulls 4 Tags Updated 2 years ago
Ollama Library — Score 38.0 AI-099-nodate-model-datase-d0590ca5 Full article qwen3.5 Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance. vision tools thinking cloud 0.8b 2b 4b 9b 27b 35b 122b 15.3M Pulls 64 Tags Updated 1 month ago
Ollama Library — Score 35.0 AI-099-nodate-model-datase-fc283b4a Full article phi3 Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsoft. 3.8b 14b 17.8M Pulls 72 Tags Updated 1 year ago
Ollama Library — Score 35.0 AI-099-nodate-model-datase-74c2856b Full article qwen2.5-coder The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing. tools 0.5b 1.5b 3b 7b 14b 32b 18.4M Pulls 199 Tags Updated 1 year ago
Ollama Library — Score 33.0 AI-099-nodate-model-datase-4d541c0e Full article llama3 Meta Llama 3: The most capable openly available LLM to date 8b 70b 24.7M Pulls 68 Tags Updated 2 years ago
Ollama Library — Score 30.0 AI-099-nodate-model-datase-904b1b4f Full article gemma2 Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B. 2b 9b 27b 27.5M Pulls 94 Tags Updated 1 year ago
Ollama Library — Score 48.0 AI-099-nodate-model-datase-112edf7b Full article mistral The 7B model released by Mistral AI, updated to version 0.3. tools 7b 31M Pulls 84 Tags Updated 12 months ago
Ollama Library — Score 30.0 AI-099-nodate-model-datase-f5bbcc33 Full article gemma3 The current, most capable model that runs on a single GPU. vision cloud 270m 1b 4b 12b 27b 38.5M Pulls 29 Tags Updated 7 months ago
Ollama Library — Score 38.0 AI-099-nodate-model-datase-acf2da58 Full article llama3.2 Meta's Llama 3.2 goes small with 1B and 3B models. tools 1b 3b 76.1M Pulls 63 Tags Updated 1 year ago
Ollama Library — Score 27.0 AI-099-nodate-model-datase-2840df7c Full article nomic-embed-text A high-performing open embedding model with a large token context window. embedding 78M Pulls 3 Tags Updated 2 years ago
Ollama Library — Score 43.0 AI-099-nodate-model-datase-27db67ec Full article llama3.1 Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes. tools 8b 70b 405b 117M Pulls 93 Tags Updated 1 year ago
OECD AI Wonk Blog — Score 27.0 USR-0164-nodate-ai-specialis-b23ac963 Full article Policy areas Browse OECD work related to AI across policy areas.