Starter version, in progress These lists are snapshots we refresh by hand for now. Automatic daily refresh is planned.
Top AI models by human votes
People compare two anonymous AI answers and vote for the better one. The score works like chess Elo: higher means it wins more often.
| # | Model | Maker | Score |
|---|---|---|---|
| 1 | Gemini 4 Carbon (High) | 1526±10 (preliminary) | |
| 2 | Gemini 4 Argon (High) | 1522±5 | |
| 3 | Muse Wonder (Max) | Meta | 1511±6 |
| 4 | Claude Opus 5.5 (High) | Anthropic | 1507±6 |
| 5 | Claude Fable 5 (High) | Anthropic | 1504±4 |
| 6 | Claude Opus 4.6 (High) | Anthropic | 1503±3 |
| 7 | Claude Fable 5.1 (Max) | Anthropic | 1502±5 |
| 8 | Claude Opus 4.7 (High) | Anthropic | 1501±4 |
| 9 | Gemini 3.8 Flash (High) | 1497±4 (preliminary) | |
| 10 | Muse Spark 1.3 (Max) | Meta | 1497±5 |
Source: LMArena Text Arena, Overall, leaderboard dated Nov 11, 2026. Checked Nov 17, 2026. Scores have error bars (±); models within a few points are effectively tied.
Trending models on Hugging Face
| # | Model | Type | Likes |
|---|---|---|---|
| 1 | MiniMaxAI/MiniMax-H3-Image | text-to-image | 1,427 |
| 2 | Qwen/Qwen3.8-27B | image-text-to-text | 20,401 |
| 3 | Lightricks/LTX-2.5 | image-to-video | 12,380 |
| 4 | higurashi-ai/Haru-4B | audio-to-audio | 488 |
| 5 | thinkingmachines/Inkling-2-Small | image-text-to-text | 438 |
| 6 | unsloth/Qwen3.8-27B-GGUF | – | 6,131 |
| 7 | Comfy-Org/MiniMax-H3-Image | text-to-image | 516 |
| 8 | black-forest-labs/flux-3-image-klein-comfy | image-to-image | 3,401 |
Source: Hugging Face, models sorted by trending (public API). Checked Nov 17, 2026, 3:45 PM ET. We skip models labeled “uncensored”. Listing is not an endorsement.
Top AI repos on GitHub
| # | Repository | Stars |
|---|---|---|
| 1 | affaan-m/ECC The agent harness performance optimization system. Skills, instincts, memory, security, and research-first dev | 305,357 |
| 2 | NousResearch/hermes-agent The agent that grows with you | 264,179 |
| 3 | firecrawl/firecrawl Knowledge infrastructure to make your agents smarter. Search, scrape and 550+ data providers through one API. | 202,605 |
| 4 | DietrichGebert/ponytail Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. | 192,922 |
| 5 | Significant-Gravitas/AutoGPT AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the too | 188,078 |
| 6 | ollama/ollama Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. | 187,417 |
| 7 | f/prompts.chat f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source | 177,756 |
| 8 | huggingface/transformers 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, a | 169,325 |
| 9 | langgenius/dify Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. De | 161,371 |
| 10 | open-webui/open-webui User-friendly AI Interface (Supports Ollama, OpenAI API, ...) | 158,952 |
Source: GitHub, topic “llm”, sorted by stars (public search API). Checked Nov 17, 2026, 3:45 PM ET. Stars measure popularity, not quality.