lechmazur / nyt-connectionsLinks
Benchmark that evaluates LLMs using 651 NYT Connections puzzles extended with extra trick words
☆130Updated this week
Alternatives and similar repositories for nyt-connections
Users that are interested in nyt-connections are comparing it to the libraries listed below
Sorting:
- Pivotal Token Search☆109Updated this week
- Hallucinations (Confabulations) Document-Based Benchmark for RAG. Includes human-verified questions and answers.☆183Updated last week
- A multi-player tournament benchmark that tests LLMs in social reasoning, strategy, and deception. Players engage in public and private co…☆282Updated this week
- Thematic Generalization Benchmark: measures how effectively various LLMs can infer a narrow or specific "theme" (category/rule) from a sm…☆60Updated this week
- An LLM trained only on data from certain time periods to reduce modern bias☆197Updated this week
- Multi-Agent Step Race Benchmark: Assessing LLM Collaboration and Deception Under Pressure. A multi-player “step-race” that challenges LLM…☆56Updated this week
- klmbr - a prompt pre-processing technique to break through the barrier of entropy while generating text with LLMs☆78Updated 9 months ago
- AI management tool☆118Updated 8 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆140Updated 4 months ago
- LLM Divergent Thinking Creativity Benchmark. LLMs generate 25 unique words that start with a given letter with no connections to each oth…☆31Updated 3 months ago
- Guaranteed Structured Output from any Language Model via Hierarchical State Machines☆140Updated last month
- A python package for serving LLM on OpenAI-compatible API endpoints with prompt caching using MLX.☆89Updated 2 weeks ago
- Smart proxy for LLM APIs that enables model-specific parameter control, automatic mode switching (like Qwen3's /think and /no_think), and…☆48Updated last month
- ☆130Updated 2 months ago
- Glyphs, acting as collaboratively defined symbols linking related concepts, add a layer of multidimensional semantic richness to user-AI …☆49Updated 5 months ago
- ☆101Updated last month
- Conduct in-depth research with AI-driven insights : DeepDive is a command-line tool that leverages web searches and AI models to generate…☆42Updated 10 months ago
- explore token trajectory trees on instruct and base models☆134Updated last month
- Public Goods Game (PGG) Benchmark: Contribute & Punish is a multi-agent benchmark that tests cooperative and self-interested strategies a…☆37Updated 3 months ago
- This small API downloads and exposes access to NeuML's txtai-wikipedia and full wikipedia datasets, taking in a query and returning full …☆98Updated this week
- This project is a reverse-engineered version of Figma's tone changer. It uses Groq's Llama-3-8b for high-speed inference and to adjust th…☆89Updated 11 months ago
- ☆116Updated 5 months ago
- An extension that lets the AI take the wheel, allowing it to use the mouse and keyboard, recognize UI elements, and prompt itself :3...no…☆125Updated 8 months ago
- Testing LLM reasoning abilities with family relationship quizzes.☆62Updated 5 months ago
- Useful resources for LLM-based Diarization and Transcription.☆55Updated 9 months ago
- Claude Deep Research config for Claude Code.☆196Updated 4 months ago
- Efficient computer use agent powered by Meta Llama 4 Maverick☆40Updated 3 months ago
- ☆214Updated last month
- ☆95Updated 6 months ago
- Self-hosted LLM chatbot arena, with yourself as the only judge☆41Updated last year