The EVA Directive is Active. We're calling on Reality Architects to locate the flaw in a perfect system.

2077AI

Revolutionizing AI Data

The 2077AI Foundation, is at the forefront of AI data standardization and progression. Our goal is unlocking greater value from data, accelerating AI development, and fostering an efficient, prosperous AI data ecosystem. Utilizing a $10.24 million investment, we're committed to promoting open source initiatives and invite you to join us in shaping the future of AI.

DataSets

OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations: OmniDocBench is a comprehensive benchmark for evaluating AI in document parsing and content extraction.

OmniDocBench

OmniDocBench is a comprehensive benchmark for evaluating AI in document parsing and content extraction.

EditReward

EDITREWARD is trained with our new large-scale human preference dataset, meticulously annotated by trained experts following a rigorous protocol containing over 200K preference pairs.

VideoScore2

VideoScore2 is a multi-dimensional, interpretable, and human-aligned framework that explicitly evaluates visual quality,text-to-video alignment, and physical/common-sense consistency while producing detailed chain-of-thought rationales.

AutoKaggle

AutoKaggle is a powerful and user-centric framework that assists data scientists in completing daily data pipelines through a collaborative multi-agent system. AutoKaggle implements an iterative development process that combines code execution, debugging, and comprehensive unit testing to ensure code correctness and logic consistency.

Chain-of-Agents

Chain-of-Agents (CoA) is a novel framework for training end-to-end agent foundation models (AFM) using multi-agent distillation and agentic reinforcement learning. Our approach addresses key challenges in developing versatile AI agents that can perform complex tasks across diverse domains.

YuE: Open Music Foundation Models for Full-Song Generation

YuE

YuE is a family of open foundation models based on the LLaMA2 architecture. Specifically, YuE scales to trillions of tokens and generates up to five minutes of music while maintaining lyrical alignment, coherent musical structure, and engaging vocal melodies with appropriate accompaniment.

KOR-BENCH

Knowledge-Orthogonal Reasoning Benchmark (KOR-Bench) is designed to evaluate models‘ intrinsic reasoning and planning abilities by minimizing interference from pretrained knowledge. It introduces new rules that are independent of prior knowledge, allowing for a more accurate assessment of how models adapt to novel rule-driven tasks.

SuperGPQA

SuperGPQA is a large-scale and highly challenging benchmark created to evaluate the advanced reasoning capabilities of Large Language Models (LLMs). Its purpose is to test model performance on expert-level, graduate qualification questions across an unprecedented 285 academic and professional disciplines.

M-A-P Matrix

Matrix is a massive, open-source pretraining dataset containing approximately 4.7 trillion tokens** of bilingual text in English and Chinese.

VeriGUI

VeriGUI is a large-scale benchmark designed to evaluate and advance the capabilities of GUI agents in the challenging domain of long-horizon, verifiable task automation.

AFM-Datasets

AFM-Datasets is the official training dataset released with the research paper, "Chain-of-Agents," and is specifically designed for building Agent Foundation Models (AFMs).

TaskCraft

TaskCraft is a multi-modal benchmark dataset featuring tasks ranging from simple (1-step) to expert-level (4-step+).

CriticLeanBench

CriticLeanBench is a specialized benchmark designed to evaluate the critical reasoning of AI models, specifically on the task of validating the translation of natural language mathematics into formal Lean 4 theorem statements.

MMAR

MMAR (Massive Multi-disciplinary Audio Reasoning) is a new and challenging benchmark designed to evaluate the deep reasoning capabilities of Audio-Language Models (ALMs).

FormalMATH

FormalMATH is a large-scale benchmark designed to evaluate and advance the capabilities of Large Language Models in the challenging domain of formal mathematical reasoning.

COIG-P

COIG-P (Chinese Open Instruction Generalist - Preference) is a high-quality, large-scale Chinese preference dataset designed for aligning Large Language Models (LLMs) with human values.

OmniDocBench

OmniDocBench is a comprehensive benchmark for evaluating AI in document parsing and content extraction.

EditReward

EDITREWARD is trained with our new large-scale human preference dataset, meticulously annotated by trained experts following a rigorous protocol containing over 200K preference pairs.

VideoScore2

AutoKaggle

Chain-of-Agents

YuE

KOR-BENCH

SuperGPQA

M-A-P Matrix

Matrix is a massive, open-source pretraining dataset containing approximately 4.7 trillion tokens** of bilingual text in English and Chinese.

VeriGUI

VeriGUI is a large-scale benchmark designed to evaluate and advance the capabilities of GUI agents in the challenging domain of long-horizon, verifiable task automation.

AFM-Datasets

AFM-Datasets is the official training dataset released with the research paper, "Chain-of-Agents," and is specifically designed for building Agent Foundation Models (AFMs).

TaskCraft

TaskCraft is a multi-modal benchmark dataset featuring tasks ranging from simple (1-step) to expert-level (4-step+).

CriticLeanBench

MMAR

MMAR (Massive Multi-disciplinary Audio Reasoning) is a new and challenging benchmark designed to evaluate the deep reasoning capabilities of Audio-Language Models (ALMs).

FormalMATH

FormalMATH is a large-scale benchmark designed to evaluate and advance the capabilities of Large Language Models in the challenging domain of formal mathematical reasoning.

COIG-P

COIG-P (Chinese Open Instruction Generalist - Preference) is a high-quality, large-scale Chinese preference dataset designed for aligning Large Language Models (LLMs) with human values.

Blog/Featured

Introducing EDITREWARD: The AI Judge That’s Closing the Gap in Open-Source Image Editing

Unlocking Deeper Multimodal Understanding: Introducing PIN-200M, A Massive Dataset for Next-Gen LMMs

Introducing Chain-of-Agents: A New Paradigm for Agent Foundation Model

Unveiling GPT-5’s Two Faces: SuperGPQA Benchmark Analysis

VeriGUI: The Open-Source Benchmark Testing AI Agents Real-World Capabilities

Creative Writing Dataset with Thought Processes: Unleashing Human-like Creativity in AI

Proudly Announce Abaka AI Join 2077AI Community as Core Founding Contributor

FormalMATH Benchmark: A Formal Mathematics Benchmark for Pushing the Limits of AI

Breaking Traditional Knowledge Dependency: KOR-Bench for Evaluating Intrinsic Reasoning Abilities of Models

A Novel Paradigm for Model Evaluation: The Innovative Multi-source Document Parsing Evaluation Framework OmniDocBench

OmniHD-Scenes: A Next-Generation Multimodal Dataset for Autonomous Driving

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines - Exploring the Real Proficiency Boundaries of LLM

Matrix Dataset: A Revolutionary Bilingual AI Pre-training Corpus

PIN Dataset: A Unified Paradigm for Multimodal Learning

+more

Blog

Insights and narratives surrounding the 2077AI Project, focusing on aspects like dataset development and model evaluation.

Project-EVA

Paper

2077AI

Revolutionizing AI Data

DataSets

OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations: OmniDocBench is a comprehensive benchmark for evaluating AI in document parsing and content extraction.

OmniDocBench

EditReward

VideoScore2

AutoKaggle

Chain-of-Agents

YuE

KOR-BENCH

SuperGPQA

M-A-P Matrix

VeriGUI

AFM-Datasets

TaskCraft

CriticLeanBench

MMAR

FormalMATH

COIG-P

OmniDocBench

EditReward

VideoScore2

AutoKaggle

Chain-of-Agents

YuE

KOR-BENCH

SuperGPQA

M-A-P Matrix

VeriGUI

AFM-Datasets

TaskCraft

CriticLeanBench

MMAR

FormalMATH

COIG-P

Blog/Featured

Introducing EDITREWARD: The AI Judge That’s Closing the Gap in Open-Source Image Editing

Unlocking Deeper Multimodal Understanding: Introducing PIN-200M, A Massive Dataset for Next-Gen LMMs

Introducing Chain-of-Agents: A New Paradigm for Agent Foundation Model

Unveiling GPT-5’s Two Faces: SuperGPQA Benchmark Analysis

VeriGUI: The Open-Source Benchmark Testing AI Agents Real-World Capabilities

Creative Writing Dataset with Thought Processes: Unleashing Human-like Creativity in AI

Proudly Announce Abaka AI Join 2077AI Community as Core Founding Contributor

FormalMATH Benchmark: A Formal Mathematics Benchmark for Pushing the Limits of AI

Breaking Traditional Knowledge Dependency: KOR-Bench for Evaluating Intrinsic Reasoning Abilities of Models

A Novel Paradigm for Model Evaluation: The Innovative Multi-source Document Parsing Evaluation Framework OmniDocBench

OmniHD-Scenes: A Next-Generation Multimodal Dataset for Autonomous Driving

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines - Exploring the Real Proficiency Boundaries of LLM

Matrix Dataset: A Revolutionary Bilingual AI Pre-training Corpus

PIN Dataset: A Unified Paradigm for Multimodal Learning

Blog

Introducing EDITREWARD: The AI Judge That’s Closing the Gap in Open-Source Image Editing

Unlocking Deeper Multimodal Understanding: Introducing PIN-200M, A Massive Dataset for Next-Gen LMMs

Introducing Chain-of-Agents: A New Paradigm for Agent Foundation Model

Unveiling GPT-5’s Two Faces: SuperGPQA Benchmark Analysis

VeriGUI: The Open-Source Benchmark Testing AI Agents Real-World Capabilities

Creative Writing Dataset with Thought Processes: Unleashing Human-like Creativity in AI