
MMMU
This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"
Stars: 374

MMMU is a benchmark designed to evaluate multimodal models on college-level subject knowledge tasks, covering 30 subjects and 183 subfields with 11.5K questions. It focuses on advanced perception and reasoning with domain-specific knowledge, challenging models to perform tasks akin to those faced by experts. The evaluation of various models highlights substantial challenges, with room for improvement to stimulate the community towards expert artificial general intelligence (AGI).
README:
π Homepage | π Leaderboard | π€ MMMU-Pro | π MMMU-Pro arXiv | π€ MMMU | π MMMU arXiv
This repo contains the evaluation code for the paper "MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark" and "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"
- π₯[2024-09-05] Introducing MMMU-Pro, a robust version of MMMU benchmark for multimodal AI evaluation! π
- π[2024-01-31]: We added Human Expert performance on the Leaderboard!π
- π₯[2023-12-04]: Our evaluation server for test set is now availble on EvalAI. We welcome all submissions and look forward to your participation! π
MMMU is a new benchmark designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning. MMMU includes 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering. These questions span 30 subjects and 183 subfields, comprising 32 highly heterogeneous image types, such as charts, diagrams, maps, tables, music sheets, and chemical structures. Unlike existing benchmarks, MMMU focuses on advanced perception and reasoning with domain-specific knowledge, challenging models to perform tasks akin to those faced by experts. Our evaluation of 14 open-source LMMs and the proprietary GPT-4V(ision) highlights the substantial challenges posed by MMMU. Even the advanced GPT-4V only achieves a 56% accuracy, indicating significant room for improvement. We believe MMMU will stimulate the community to build next-generation multimodal foundation models towards expert artificial general intelligence (AGI).
Building upon MMMU, MMMU-Pro introduces even more stringent assessment methodologies to evaluate multimodal models' intrinsic understanding and reasoning capabilities. MMMU-Pro employs a meticulously structured three-step process:
- Filtering out text-only answerable questions: Ensures that the questions pressing multimodal understanding rather than purely textual comprehension.
- Augmenting candidate options: Introduces additional plausible options to make the task more challenging.
- Vision-only input setting: Embedding questions within images pushes AI to "see" and "read" simultaneously, replicating a core human cognitive skill of integrating visual and textual information.
Our results reveal that model performance on MMMU-Pro is significantly lower than on MMMU, with accuracies ranging from 16.8% to 26.9% across various models. We investigate the effects of OCR prompts and Chain of Thought (CoT) reasoning. OCR prompts have minimal impact, while CoT generally enhances performance. MMMU-Pro offers a more rigorous evaluation framework, closely reflecting real-world scenarios and providing critical insights for advancing multimodal AI research.
MMMU and MMMU-Pro were meticulously designed to challenge and evaluate multimodal models with tasks demanding college-level subject knowledge and complex reasoning. For more detailed information, please refer to our Hugging Face datasets:
Please refer to our evaluation folders for detailed information on evaluating with both MMMU and MMMU-Pro benchmarks:
π― MMMU Evaluation
- We have released a full suite comprising 150 development samples and 900 validation samples. However, the 10,500 test questions are available without their answers.
- Use the development set for few-shot/in-context learning.
- Use the validation set for debugging models, selecting hyperparameters, and quick evaluations.
The answers and explanations for the test set questions are withheld. You can submit your model's predictions for the test set on EvalAI.
The guidelines for the annotators emphasized strict compliance with copyright and licensing rules from the initial data source, specifically avoiding materials from websites that forbid copying and redistribution. Should you encounter any data samples potentially breaching the copyright or licensing regulations of any site, we encourage you to contact us. Upon verification, such samples will be promptly removed.
- Xiang Yue: [email protected]
- Yu Su: [email protected]
- Wenhu Chen: [email protected]
BibTeX:
@inproceedings{yue2023mmmu,
title={MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI},
author={Xiang Yue and Yuansheng Ni and Kai Zhang and Tianyu Zheng and Ruoqi Liu and Ge Zhang and Samuel Stevens and Dongfu Jiang and Weiming Ren and Yuxuan Sun and Cong Wei and Botao Yu and Ruibin Yuan and Renliang Sun and Ming Yin and Boyuan Zheng and Zhenzhu Yang and Yibo Liu and Wenhao Huang and Huan Sun and Yu Su and Wenhu Chen},
booktitle={Proceedings of CVPR},
year={2024},
}
@article{yue2024mmmu,
title={MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark},
author={Xiang Yue and Tianyu Zheng and Yuansheng Ni and Yubo Wang and Kai Zhang and Shengbang Tong and Yuxuan Sun and Botao Yu and Ge Zhang and Huan Sun and Yu Su and Wenhu Chen and Graham Neubig},
journal={arXiv preprint arXiv:2409.02813},
year={2024}
}
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for MMMU
Similar Open Source Tools

MMMU
MMMU is a benchmark designed to evaluate multimodal models on college-level subject knowledge tasks, covering 30 subjects and 183 subfields with 11.5K questions. It focuses on advanced perception and reasoning with domain-specific knowledge, challenging models to perform tasks akin to those faced by experts. The evaluation of various models highlights substantial challenges, with room for improvement to stimulate the community towards expert artificial general intelligence (AGI).

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.

siiRL
siiRL is a novel, fully distributed reinforcement learning (RL) framework designed to break the scaling barriers in Large Language Models (LLMs) post-training. Developed by researchers from Shanghai Innovation Institute, siiRL delivers near-linear scalability, dramatic throughput gains, and unprecedented flexibility for RL-based LLM development. It eliminates the centralized controller common in other frameworks, enabling scalability to thousands of GPUs, achieving state-of-the-art throughput, and supporting cross-hardware compatibility. siiRL is extensively benchmarked and excels in data-intensive workloads such as long-context and multi-modal training.

FloTorch
FloTorch is an innovative product designed to simplify and optimize the decision-making process for leveraging Large Language Models (LLMs) in Retrieval Augmented Generation (RAG) systems. It focuses on providing a well-architected framework, maximizing efficiency, eliminating complexity, accelerating selection, and fostering innovation. The tool offers a streamlined, user-friendly approach to help users achieve efficiency, accuracy, and cost-effectiveness in the fast-paced digital landscape of AI.

RAGEN
RAGEN is a reinforcement learning framework designed to train reasoning-capable large language model (LLM) agents in interactive, stochastic environments. It addresses challenges such as multi-turn interactions and stochastic environments through a Markov Decision Process (MDP) formulation, Reason-Interaction Chain Optimization (RICO) algorithm, and progressive reward normalization strategies. The framework consists of MDP formulation, RICO algorithm with rollout and update stages, and reward normalization strategies to stabilize training. RAGEN aims to optimize reasoning and action strategies for LLM agents operating in complex environments.

ai-notes
Notes on AI state of the art, with a focus on generative and large language models. These are the "raw materials" for the https://lspace.swyx.io/ newsletter. This repo used to be called https://github.com/sw-yx/prompt-eng, but was renamed because Prompt Engineering is Overhyped. This is now an AI Engineering notes repo.

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.

postgresml
PostgresML is a powerful Postgres extension that seamlessly combines data storage and machine learning inference within your database. It enables running machine learning and AI operations directly within PostgreSQL, leveraging GPU acceleration for faster computations, integrating state-of-the-art large language models, providing built-in functions for text processing, enabling efficient similarity search, offering diverse ML algorithms, ensuring high performance, scalability, and security, supporting a wide range of NLP tasks, and seamlessly integrating with existing PostgreSQL tools and client libraries.

Zettelgarden
Zettelgarden is a human-centric, open-source personal knowledge management system that helps users develop and maintain their understanding of the world. It focuses on creating and connecting atomic notes, thoughtful AI integration, and scalability from personal notes to company knowledge bases. The project is actively evolving, with features subject to change based on community feedback and development priorities.

RetouchGPT
RetouchGPT is a novel framework designed for interactive face retouching using Large Language Models (LLMs). It leverages instruction-driven imperfection prediction and LLM-based embedding to guide the retouching process. The tool allows users to interactively modify imperfection features in face images, achieving high-fidelity retouching results. RetouchGPT outperforms existing methods by integrating textual and visual features to accurately identify imperfections and replace them with normal skin features.

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.

long-llms-learning
A repository sharing the panorama of the methodology literature on Transformer architecture upgrades in Large Language Models for handling extensive context windows, with real-time updating the newest published works. It includes a survey on advancing Transformer architecture in long-context large language models, flash-ReRoPE implementation, latest news on data engineering, lightning attention, Kimi AI assistant, chatglm-6b-128k, gpt-4-turbo-preview, benchmarks like InfiniteBench and LongBench, long-LLMs-evals for evaluating methods for enhancing long-context capabilities, and LLMs-learning for learning technologies and applicated tasks about Large Language Models.

core
CORE is an open-source unified, persistent memory layer for all AI tools, allowing developers to maintain context across different tools like Cursor, ChatGPT, and Claude. It aims to solve the issue of context switching and information loss between sessions by creating a knowledge graph that remembers conversations, decisions, and insights. With features like unified memory, temporal knowledge graph, browser extension, chat with memory, auto-sync from apps, and MCP integration hub, CORE provides a seamless experience for managing and recalling context. The tool's ingestion pipeline captures evolving context through normalization, extraction, resolution, and graph integration, resulting in a dynamic memory that grows and changes with the user. When recalling from memory, CORE utilizes search, re-ranking, filtering, and output to provide relevant and contextual answers. Security measures include data encryption, authentication, access control, and vulnerability reporting.

MathCoder
MathCoder is a repository focused on enhancing mathematical reasoning by fine-tuning open-source language models to use code for modeling and deriving math equations. It introduces MathCodeInstruct dataset with solutions interleaving natural language, code, and execution results. The repository provides MathCoder models capable of generating code-based solutions for challenging math problems, achieving state-of-the-art scores on MATH and GSM8K datasets. It offers tools for model deployment, inference, and evaluation, along with a citation for referencing the work.

ScholarCopilot
Scholar Copilot is an intelligent academic writing assistant that enhances the research writing process through AI-powered text completion and citation suggestions. It aims to streamline academic writing while maintaining high scholarly standards. The tool provides features such as smart text generation with next-3-sentence suggestions, full section auto-completion, and context-aware writing. It also offers intelligent citation management with real-time citation suggestions, one-click citation insertion, and citation Bibtex generation. Scholar Copilot employs a unified model architecture that integrates retrieval and generation through a dynamic switching mechanism, ensuring coherent text generation with appropriate citation points.
For similar tasks

MMMU
MMMU is a benchmark designed to evaluate multimodal models on college-level subject knowledge tasks, covering 30 subjects and 183 subfields with 11.5K questions. It focuses on advanced perception and reasoning with domain-specific knowledge, challenging models to perform tasks akin to those faced by experts. The evaluation of various models highlights substantial challenges, with room for improvement to stimulate the community towards expert artificial general intelligence (AGI).

labelbox-python
Labelbox is a data-centric AI platform for enterprises to develop, optimize, and use AI to solve problems and power new products and services. Enterprises use Labelbox to curate data, generate high-quality human feedback data for computer vision and LLMs, evaluate model performance, and automate tasks by combining AI and human-centric workflows. The academic & research community uses Labelbox for cutting-edge AI research.

promptfoo
Promptfoo is a tool for testing and evaluating LLM output quality. With promptfoo, you can build reliable prompts, models, and RAGs with benchmarks specific to your use-case, speed up evaluations with caching, concurrency, and live reloading, score outputs automatically by defining metrics, use as a CLI, library, or in CI/CD, and use OpenAI, Anthropic, Azure, Google, HuggingFace, open-source models like Llama, or integrate custom API providers for any LLM API.

vespa
Vespa is a platform that performs operations such as selecting a subset of data in a large corpus, evaluating machine-learned models over the selected data, organizing and aggregating it, and returning it, typically in less than 100 milliseconds, all while the data corpus is continuously changing. It has been in development for many years and is used on a number of large internet services and apps which serve hundreds of thousands of queries from Vespa per second.

python-aiplatform
The Vertex AI SDK for Python is a library that provides a convenient way to use the Vertex AI API. It offers a high-level interface for creating and managing Vertex AI resources, such as datasets, models, and endpoints. The SDK also provides support for training and deploying custom models, as well as using AutoML models. With the Vertex AI SDK for Python, you can quickly and easily build and deploy machine learning models on Vertex AI.

ScandEval
ScandEval is a framework for evaluating pretrained language models on mono- or multilingual language tasks. It provides a unified interface for benchmarking models on a variety of tasks, including sentiment analysis, question answering, and machine translation. ScandEval is designed to be easy to use and extensible, making it a valuable tool for researchers and practitioners alike.

opencompass
OpenCompass is a one-stop platform for large model evaluation, aiming to provide a fair, open, and reproducible benchmark for large model evaluation. Its main features include: * Comprehensive support for models and datasets: Pre-support for 20+ HuggingFace and API models, a model evaluation scheme of 70+ datasets with about 400,000 questions, comprehensively evaluating the capabilities of the models in five dimensions. * Efficient distributed evaluation: One line command to implement task division and distributed evaluation, completing the full evaluation of billion-scale models in just a few hours. * Diversified evaluation paradigms: Support for zero-shot, few-shot, and chain-of-thought evaluations, combined with standard or dialogue-type prompt templates, to easily stimulate the maximum performance of various models. * Modular design with high extensibility: Want to add new models or datasets, customize an advanced task division strategy, or even support a new cluster management system? Everything about OpenCompass can be easily expanded! * Experiment management and reporting mechanism: Use config files to fully record each experiment, and support real-time reporting of results.

flower
Flower is a framework for building federated learning systems. It is designed to be customizable, extensible, framework-agnostic, and understandable. Flower can be used with any machine learning framework, for example, PyTorch, TensorFlow, Hugging Face Transformers, PyTorch Lightning, scikit-learn, JAX, TFLite, MONAI, fastai, MLX, XGBoost, Pandas for federated analytics, or even raw NumPy for users who enjoy computing gradients by hand.
For similar jobs

Perplexica
Perplexica is an open-source AI-powered search engine that utilizes advanced machine learning algorithms to provide clear answers with sources cited. It offers various modes like Copilot Mode, Normal Mode, and Focus Modes for specific types of questions. Perplexica ensures up-to-date information by using SearxNG metasearch engine. It also features image and video search capabilities and upcoming features include finalizing Copilot Mode and adding Discover and History Saving features.

KULLM
KULLM (ꡬλ¦) is a Korean Large Language Model developed by Korea University NLP & AI Lab and HIAI Research Institute. It is based on the upstage/SOLAR-10.7B-v1.0 model and has been fine-tuned for instruction. The model has been trained on 8ΓA100 GPUs and is capable of generating responses in Korean language. KULLM exhibits hallucination and repetition phenomena due to its decoding strategy. Users should be cautious as the model may produce inaccurate or harmful results. Performance may vary in benchmarks without a fixed system prompt.

MMMU
MMMU is a benchmark designed to evaluate multimodal models on college-level subject knowledge tasks, covering 30 subjects and 183 subfields with 11.5K questions. It focuses on advanced perception and reasoning with domain-specific knowledge, challenging models to perform tasks akin to those faced by experts. The evaluation of various models highlights substantial challenges, with room for improvement to stimulate the community towards expert artificial general intelligence (AGI).

1filellm
1filellm is a command-line data aggregation tool designed for LLM ingestion. It aggregates and preprocesses data from various sources into a single text file, facilitating the creation of information-dense prompts for large language models. The tool supports automatic source type detection, handling of multiple file formats, web crawling functionality, integration with Sci-Hub for research paper downloads, text preprocessing, and token count reporting. Users can input local files, directories, GitHub repositories, pull requests, issues, ArXiv papers, YouTube transcripts, web pages, Sci-Hub papers via DOI or PMID. The tool provides uncompressed and compressed text outputs, with the uncompressed text automatically copied to the clipboard for easy pasting into LLMs.

gpt-researcher
GPT Researcher is an autonomous agent designed for comprehensive online research on a variety of tasks. It can produce detailed, factual, and unbiased research reports with customization options. The tool addresses issues of speed, determinism, and reliability by leveraging parallelized agent work. The main idea involves running 'planner' and 'execution' agents to generate research questions, seek related information, and create research reports. GPT Researcher optimizes costs and completes tasks in around 3 minutes. Features include generating long research reports, aggregating web sources, an easy-to-use web interface, scraping web sources, and exporting reports to various formats.

ChatTTS
ChatTTS is a generative speech model optimized for dialogue scenarios, providing natural and expressive speech synthesis with fine-grained control over prosodic features. It supports multiple speakers and surpasses most open-source TTS models in terms of prosody. The model is trained with 100,000+ hours of Chinese and English audio data, and the open-source version on HuggingFace is a 40,000-hour pre-trained model without SFT. The roadmap includes open-sourcing additional features like VQ encoder, multi-emotion control, and streaming audio generation. The tool is intended for academic and research use only, with precautions taken to limit potential misuse.

HebTTS
HebTTS is a language modeling approach to diacritic-free Hebrew text-to-speech (TTS) system. It addresses the challenge of accurately mapping text to speech in Hebrew by proposing a language model that operates on discrete speech representations and is conditioned on a word-piece tokenizer. The system is optimized using weakly supervised recordings and outperforms diacritic-based Hebrew TTS systems in terms of content preservation and naturalness of generated speech.

do-research-in-AI
This repository is a collection of research lectures and experience sharing posts from frontline researchers in the field of AI. It aims to help individuals upgrade their research skills and knowledge through insightful talks and experiences shared by experts. The content covers various topics such as evaluating research papers, choosing research directions, research methodologies, and tips for writing high-quality scientific papers. The repository also includes discussions on academic career paths, research ethics, and the emotional aspects of research work. Overall, it serves as a valuable resource for individuals interested in advancing their research capabilities in the field of AI.