![TurtleBenchmark](/statics/github-mark.png)
TurtleBenchmark
Benchmark for LLM Reasoning & Understanding with Challenging Tasks from Real Users.
Stars: 103
![screenshot](/screenshots_githubs/mazzzystar-TurtleBenchmark.jpg)
Turtle Benchmark is a novel and cheat-proof benchmark test used to evaluate large language models (LLMs). It is based on the Turtle Soup game, focusing on logical reasoning and context understanding abilities. The benchmark does not require background knowledge or model memory, providing all necessary information for judgment from stories under 200 words. The results are objective and unbiased, quantifiable as correct/incorrect/unknown, and impossible to cheat due to using real user-generated questions and dynamic data generation during online gameplay.
README:
Turtle Benchmark is a novel, uncheatable benchmark for evaluating Large Language Models (LLMs) based on the "Turtle Soup"(海龟汤) game, focusing on logical reasoning and contextual understanding.
- Objective and Unbiased: Eliminates the need for background knowledge, focusing purely on reasoning abilities.
- Quantifiable Results: Clear, measurable outcomes (correct/incorrect/unknown) for easy comparison.
- Constantly Evolving: Uses real user-generated questions, making it impossible to "game" the system.
- Language Understanding: Tests the model's ability to comprehend context and make logical inferences.
pip install -r requirements.txt
cd evaluation
mv .env.example .env
# add API key.
# Evaluate Chinese or English.
cd english
# 0-shot for fast & cheap, 2-shot for better performance. default: 0-shot.
python evaluate.py
- 32 unique "Turtle Soup" stories.
- 1532 human-annotated labels from users' questions.
- Our evaluation log.
The overall accuracy of each model across all test cases.
To mitigate potential bias from models performing poorly on specific stories with a large number of test samples, we calculated the average accuracy for each model across all 32 stories individually.
This scatter plot compares the overall accuracy (x-axis) with the average story accuracy (y-axis) for each model in the 2-shot learning scenario.
Based on these results, we can clearly see the performance differences among the various models:
-
First Tier: Claude 3.5 Sonnet stands out as the undisputed leader, significantly outperforming all other models.
-
Second Tier: GPT-4o, Qwen-2(通义千问), Moonshot AI(月之暗面), LLama3.1 405B, and Minimax form the second tier. While we've avoided further subdivisions, there's a noticeable decrease in performance within this group, following the order listed.
-
Third Tier: Douban(豆包), DeepSeek, and LLama3.1 70B constitute the third tier.
-
Fourth Tier: GPT-4o-mini stands alone in the fourth tier.
-
Obsolete: GPT-3.5's performance suggests it's no longer competitive in this context.
It's important to note that this evaluation specifically targets the models' Chinese language understanding and reasoning capabilities. In the future, pending resources and funding, we plan to translate all stories and test questions into English and re-run the tests using English prompts. This will help eliminate any performance discrepancies that may be attributed to language differences.
We would like to express our gratitude to:
- Steven Shi (石允丰) from 5Y Capital for his generous financial support of the token usage required for this research.
- Jerry Zhao (赵乾之) for his invaluable assistance in annotating over 26,000 data points.
Your contributions have been instrumental in making this benchmark possible.
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for TurtleBenchmark
Similar Open Source Tools
![TurtleBenchmark Screenshot](/screenshots_githubs/mazzzystar-TurtleBenchmark.jpg)
TurtleBenchmark
Turtle Benchmark is a novel and cheat-proof benchmark test used to evaluate large language models (LLMs). It is based on the Turtle Soup game, focusing on logical reasoning and context understanding abilities. The benchmark does not require background knowledge or model memory, providing all necessary information for judgment from stories under 200 words. The results are objective and unbiased, quantifiable as correct/incorrect/unknown, and impossible to cheat due to using real user-generated questions and dynamic data generation during online gameplay.
![Controllable-RAG-Agent Screenshot](/screenshots_githubs/NirDiamant-Controllable-RAG-Agent.jpg)
Controllable-RAG-Agent
This repository contains a sophisticated deterministic graph-based solution for answering complex questions using a controllable autonomous agent. The solution is designed to ensure that answers are solely based on the provided data, avoiding hallucinations. It involves various steps such as PDF loading, text preprocessing, summarization, database creation, encoding, and utilizing large language models. The algorithm follows a detailed workflow involving planning, retrieval, answering, replanning, content distillation, and performance evaluation. Heuristics and techniques implemented focus on content encoding, anonymizing questions, task breakdown, content distillation, chain of thought answering, verification, and model performance evaluation.
![AI2BMD Screenshot](/screenshots_githubs/microsoft-AI2BMD.jpg)
AI2BMD
AI2BMD is a program for efficiently simulating protein molecular dynamics with ab initio accuracy. The repository contains datasets, simulation programs, and public materials related to AI2BMD. It provides a Docker image for easy deployment and a standalone launcher program. Users can run simulations by downloading the launcher script and specifying simulation parameters. The repository also includes ready-to-use protein structures for testing. AI2BMD is designed for x86-64 GNU/Linux systems with recommended hardware specifications. The related research includes model architectures like ViSNet, Geoformer, and fine-grained force metrics for MLFF. Citation information and contact details for the AI2BMD Team are provided.
![fuse-med-ml Screenshot](/screenshots_githubs/BiomedSciAI-fuse-med-ml.jpg)
fuse-med-ml
FuseMedML is a Python framework designed to accelerate machine learning-based discovery in the medical field by promoting code reuse. It provides a flexible design concept where data is stored in a nested dictionary, allowing easy handling of multi-modality information. The framework includes components for creating custom models, loss functions, metrics, and data processing operators. Additionally, FuseMedML offers 'batteries included' key components such as fuse.data for data processing, fuse.eval for model evaluation, and fuse.dl for reusable deep learning components. It supports PyTorch and PyTorch Lightning libraries and encourages the creation of domain extensions for specific medical domains.
![EDA-GPT Screenshot](/screenshots_githubs/shaunthecomputerscientist-EDA-GPT.jpg)
EDA-GPT
EDA GPT is an open-source data analysis companion that offers a comprehensive solution for structured and unstructured data analysis. It streamlines the data analysis process, empowering users to explore, visualize, and gain insights from their data. EDA GPT supports analyzing structured data in various formats like CSV, XLSX, and SQLite, generating graphs, and conducting in-depth analysis of unstructured data such as PDFs and images. It provides a user-friendly interface, powerful features, and capabilities like comparing performance with other tools, analyzing large language models, multimodal search, data cleaning, and editing. The tool is optimized for maximal parallel processing, searching internet and documents, and creating analysis reports from structured and unstructured data.
![persian-license-plate-recognition Screenshot](/screenshots_githubs/mtkarimi-persian-license-plate-recognition.jpg)
persian-license-plate-recognition
The Persian License Plate Recognition (PLPR) system is a state-of-the-art solution designed for detecting and recognizing Persian license plates in images and video streams. Leveraging advanced deep learning models and a user-friendly interface, it ensures reliable performance across different scenarios. The system offers advanced detection using YOLOv5 models, precise recognition of Persian characters, real-time processing capabilities, and a user-friendly GUI. It is well-suited for applications in traffic monitoring, automated vehicle identification, and similar fields. The system's architecture includes modules for resident management, entrance management, and a detailed flowchart explaining the process from system initialization to displaying results in the GUI. Hardware requirements include an Intel Core i5 processor, 8 GB RAM, a dedicated GPU with at least 4 GB VRAM, and an SSD with 20 GB of free space. The system can be installed by cloning the repository and installing required Python packages. Users can customize the video source for processing and run the application to upload and process images or video streams. The system's GUI allows for parameter adjustments to optimize performance, and the Wiki provides in-depth information on the system's architecture and model training.
![MMStar Screenshot](/screenshots_githubs/MMStar-Benchmark-MMStar.jpg)
MMStar
MMStar is an elite vision-indispensable multi-modal benchmark comprising 1,500 challenge samples meticulously selected by humans. It addresses two key issues in current LLM evaluation: the unnecessary use of visual content in many samples and the existence of unintentional data leakage in LLM and LVLM training. MMStar evaluates 6 core capabilities across 18 detailed axes, ensuring a balanced distribution of samples across all dimensions.
![InfLLM Screenshot](/screenshots_githubs/thunlp-InfLLM.jpg)
InfLLM
InfLLM is a training-free memory-based method that unveils the intrinsic ability of LLMs to process streaming long sequences. It stores distant contexts into additional memory units and employs an efficient mechanism to lookup token-relevant units for attention computation. Thereby, InfLLM allows LLMs to efficiently process long sequences while maintaining the ability to capture long-distance dependencies. Without any training, InfLLM enables LLMs pre-trained on sequences of a few thousand tokens to achieve superior performance than competitive baselines continually training these LLMs on long sequences. Even when the sequence length is scaled to 1, 024K, InfLLM still effectively captures long-distance dependencies.
![UFO Screenshot](/screenshots_githubs/microsoft-UFO.jpg)
UFO
UFO is a UI-focused dual-agent framework to fulfill user requests on Windows OS by seamlessly navigating and operating within individual or spanning multiple applications.
![tinyllm Screenshot](/screenshots_githubs/zozoheir-tinyllm.jpg)
tinyllm
tinyllm is a lightweight framework designed for developing, debugging, and monitoring LLM and Agent powered applications at scale. It aims to simplify code while enabling users to create complex agents or LLM workflows in production. The core classes, Function and FunctionStream, standardize and control LLM, ToolStore, and relevant calls for scalable production use. It offers structured handling of function execution, including input/output validation, error handling, evaluation, and more, all while maintaining code readability. Users can create chains with prompts, LLM models, and evaluators in a single file without the need for extensive class definitions or spaghetti code. Additionally, tinyllm integrates with various libraries like Langfuse and provides tools for prompt engineering, observability, logging, and finite state machine design.
![peridyno Screenshot](/screenshots_githubs/peridyno-peridyno.jpg)
peridyno
PeriDyno is a CUDA-based, highly parallel physics engine targeted at providing real-time simulation of physical environments for intelligent agents. It is designed to be easy to use and integrate into existing projects, and it provides a wide range of features for simulating a variety of physical phenomena. PeriDyno is open source and available under the Apache 2.0 license.
![llm-course Screenshot](/screenshots_githubs/mlabonne-llm-course.jpg)
llm-course
The LLM course is divided into three parts: 1. 🧩 **LLM Fundamentals** covers essential knowledge about mathematics, Python, and neural networks. 2. 🧑🔬 **The LLM Scientist** focuses on building the best possible LLMs using the latest techniques. 3. 👷 **The LLM Engineer** focuses on creating LLM-based applications and deploying them. For an interactive version of this course, I created two **LLM assistants** that will answer questions and test your knowledge in a personalized way: * 🤗 **HuggingChat Assistant**: Free version using Mixtral-8x7B. * 🤖 **ChatGPT Assistant**: Requires a premium account. ## 📝 Notebooks A list of notebooks and articles related to large language models. ### Tools | Notebook | Description | Notebook | |----------|-------------|----------| | 🧐 LLM AutoEval | Automatically evaluate your LLMs using RunPod | ![Open In Colab](img/colab.svg) | | 🥱 LazyMergekit | Easily merge models using MergeKit in one click. | ![Open In Colab](img/colab.svg) | | 🦎 LazyAxolotl | Fine-tune models in the cloud using Axolotl in one click. | ![Open In Colab](img/colab.svg) | | ⚡ AutoQuant | Quantize LLMs in GGUF, GPTQ, EXL2, AWQ, and HQQ formats in one click. | ![Open In Colab](img/colab.svg) | | 🌳 Model Family Tree | Visualize the family tree of merged models. | ![Open In Colab](img/colab.svg) | | 🚀 ZeroSpace | Automatically create a Gradio chat interface using a free ZeroGPU. | ![Open In Colab](img/colab.svg) |
![CogVideo Screenshot](/screenshots_githubs/THUDM-CogVideo.jpg)
CogVideo
CogVideo is an open-source repository that provides pretrained text-to-video models for generating videos based on input text. It includes models like CogVideoX-2B and CogVideo, offering powerful video generation capabilities. The repository offers tools for inference, fine-tuning, and model conversion, along with demos showcasing the model's capabilities through CLI, web UI, and online experiences. CogVideo aims to facilitate the creation of high-quality videos from textual descriptions, catering to a wide range of applications.
![XLearning Screenshot](/screenshots_githubs/Qihoo360-XLearning.jpg)
XLearning
XLearning is a scheduling platform for big data and artificial intelligence, supporting various machine learning and deep learning frameworks. It runs on Hadoop Yarn and integrates frameworks like TensorFlow, MXNet, Caffe, Theano, PyTorch, Keras, XGBoost. XLearning offers scalability, compatibility, multiple deep learning framework support, unified data management based on HDFS, visualization display, and compatibility with code at native frameworks. It provides functions for data input/output strategies, container management, TensorBoard service, and resource usage metrics display. XLearning requires JDK >= 1.7 and Maven >= 3.3 for compilation, and deployment on CentOS 7.2 with Java >= 1.7 and Hadoop 2.6, 2.7, 2.8.
![ai-data-analysis-MulitAgent Screenshot](/screenshots_githubs/starpig1129-ai-data-analysis-MulitAgent.jpg)
ai-data-analysis-MulitAgent
AI-Driven Research Assistant is an advanced AI-powered system utilizing specialized agents for data analysis, visualization, and report generation. It integrates LangChain, OpenAI's GPT models, and LangGraph for complex research processes. Key features include hypothesis generation, data processing, web search, code generation, and report writing. The system's unique Note Taker agent maintains project state, reducing overhead and improving context retention. System requirements include Python 3.10+ and Jupyter Notebook environment. Installation involves cloning the repository, setting up a Conda virtual environment, installing dependencies, and configuring environment variables. Usage instructions include setting data, running Jupyter Notebook, customizing research tasks, and viewing results. Main components include agents for hypothesis generation, process supervision, visualization, code writing, search, report writing, quality review, and note-taking. Workflow involves hypothesis generation, processing, quality review, and revision. Customization is possible by modifying agent creation and workflow definition. Current issues include OpenAI errors, NoteTaker efficiency, runtime optimization, and refiner improvement. Contributions via pull requests are welcome under the MIT License.
![llmops-duke-aipi Screenshot](/screenshots_githubs/alfredodeza-llmops-duke-aipi.jpg)
llmops-duke-aipi
LLMOps Duke AIPI is a course focused on operationalizing Large Language Models, teaching methodologies for developing applications using software development best practices with large language models. The course covers various topics such as generative AI concepts, setting up development environments, interacting with large language models, using local large language models, applied solutions with LLMs, extensibility using plugins and functions, retrieval augmented generation, introduction to Python web frameworks for APIs, DevOps principles, deploying machine learning APIs, LLM platforms, and final presentations. Students will learn to build, share, and present portfolios using Github, YouTube, and Linkedin, as well as develop non-linear life-long learning skills. Prerequisites include basic Linux and programming skills, with coursework available in Python or Rust. Additional resources and references are provided for further learning and exploration.
For similar tasks
![hallucination-leaderboard Screenshot](/screenshots_githubs/vectara-hallucination-leaderboard.jpg)
hallucination-leaderboard
This leaderboard evaluates the hallucination rate of various Large Language Models (LLMs) when summarizing documents. It uses a model trained by Vectara to detect hallucinations in LLM outputs. The leaderboard includes models from OpenAI, Anthropic, Google, Microsoft, Amazon, and others. The evaluation is based on 831 documents that were summarized by all the models. The leaderboard shows the hallucination rate, factual consistency rate, answer rate, and average summary length for each model.
![h2o-llmstudio Screenshot](/screenshots_githubs/h2oai-h2o-llmstudio.jpg)
h2o-llmstudio
H2O LLM Studio is a framework and no-code GUI designed for fine-tuning state-of-the-art large language models (LLMs). With H2O LLM Studio, you can easily and effectively fine-tune LLMs without the need for any coding experience. The GUI is specially designed for large language models, and you can finetune any LLM using a large variety of hyperparameters. You can also use recent finetuning techniques such as Low-Rank Adaptation (LoRA) and 8-bit model training with a low memory footprint. Additionally, you can use Reinforcement Learning (RL) to finetune your model (experimental), use advanced evaluation metrics to judge generated answers by the model, track and compare your model performance visually, and easily export your model to the Hugging Face Hub and share it with the community.
![llm-jp-eval Screenshot](/screenshots_githubs/llm-jp-llm-jp-eval.jpg)
llm-jp-eval
LLM-jp-eval is a tool designed to automatically evaluate Japanese large language models across multiple datasets. It provides functionalities such as converting existing Japanese evaluation data to text generation task evaluation datasets, executing evaluations of large language models across multiple datasets, and generating instruction data (jaster) in the format of evaluation data prompts. Users can manage the evaluation settings through a config file and use Hydra to load them. The tool supports saving evaluation results and logs using wandb. Users can add new evaluation datasets by following specific steps and guidelines provided in the tool's documentation. It is important to note that using jaster for instruction tuning can lead to artificially high evaluation scores, so caution is advised when interpreting the results.
![Awesome-LLM Screenshot](/screenshots_githubs/Hannibal046-Awesome-LLM.jpg)
Awesome-LLM
Awesome-LLM is a curated list of resources related to large language models, focusing on papers, projects, frameworks, tools, tutorials, courses, opinions, and other useful resources in the field. It covers trending LLM projects, milestone papers, other papers, open LLM projects, LLM training frameworks, LLM evaluation frameworks, tools for deploying LLM, prompting libraries & tools, tutorials, courses, books, and opinions. The repository provides a comprehensive overview of the latest advancements and resources in the field of large language models.
![bocoel Screenshot](/screenshots_githubs/rentruewang-bocoel.jpg)
bocoel
BoCoEL is a tool that leverages Bayesian Optimization to efficiently evaluate large language models by selecting a subset of the corpus for evaluation. It encodes individual entries into embeddings, uses Bayesian optimization to select queries, retrieves from the corpus, and provides easily managed evaluations. The tool aims to reduce computation costs during evaluation with a dynamic budget, supporting models like GPT2, Pythia, and LLAMA through integration with Hugging Face transformers and datasets. BoCoEL offers a modular design and efficient representation of the corpus to enhance evaluation quality.
![cladder Screenshot](/screenshots_githubs/causalNLP-cladder.jpg)
cladder
CLadder is a repository containing the CLadder dataset for evaluating causal reasoning in language models. The dataset consists of yes/no questions in natural language that require statistical and causal inference to answer. It includes fields such as question_id, given_info, question, answer, reasoning, and metadata like query_type and rung. The dataset also provides prompts for evaluating language models and example questions with associated reasoning steps. Additionally, it offers dataset statistics, data variants, and code setup instructions for using the repository.
![uncheatable_eval Screenshot](/screenshots_githubs/Jellyfish042-uncheatable_eval.jpg)
uncheatable_eval
Uncheatable Eval is a tool designed to assess the language modeling capabilities of LLMs on real-time, newly generated data from the internet. It aims to provide a reliable evaluation method that is immune to data leaks and cannot be gamed. The tool supports the evaluation of Hugging Face AutoModelForCausalLM models and RWKV models by calculating the sum of negative log probabilities on new texts from various sources such as recent papers on arXiv, new projects on GitHub, news articles, and more. Uncheatable Eval ensures that the evaluation data is not included in the training sets of publicly released models, thus offering a fair assessment of the models' performance.
![llms Screenshot](/screenshots_githubs/IbrahimSobh-llms.jpg)
llms
The 'llms' repository is a comprehensive guide on Large Language Models (LLMs), covering topics such as language modeling, applications of LLMs, statistical language modeling, neural language models, conditional language models, evaluation methods, transformer-based language models, practical LLMs like GPT and BERT, prompt engineering, fine-tuning LLMs, retrieval augmented generation, AI agents, and LLMs for computer vision. The repository provides detailed explanations, examples, and tools for working with LLMs.
For similar jobs
![weave Screenshot](/screenshots_githubs/wandb-weave.jpg)
weave
Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.
![LLMStack Screenshot](/screenshots_githubs/trypromptly-LLMStack.jpg)
LLMStack
LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.
![VisionCraft Screenshot](/screenshots_githubs/VisionCraft-org-VisionCraft.jpg)
VisionCraft
The VisionCraft API is a free API for using over 100 different AI models. From images to sound.
![kaito Screenshot](/screenshots_githubs/Azure-kaito.jpg)
kaito
Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.
![PyRIT Screenshot](/screenshots_githubs/Azure-PyRIT.jpg)
PyRIT
PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.
![tabby Screenshot](/screenshots_githubs/TabbyML-tabby.jpg)
tabby
Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.
![spear Screenshot](/screenshots_githubs/isl-org-spear.jpg)
spear
SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.
![Magick Screenshot](/screenshots_githubs/Oneirocom-Magick.jpg)
Magick
Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.