Large Multimodal Models Evaluation: A Survey

This repository complements the paper Large Multimodal Models Evaluation: A Survey and organizes benchmarks and resources across understanding (general and specialized), generation, and community platforms. It serves as a hub for researchers to find key datasets, papers, and code.

We will continuously maintain and update this repo to ensure long-term value for the community.

Paper: SCIS Project Page: AIBench / LMM Evaluation Survey

---

Contributions

We welcome pull requests (PRs)! If you contribute five or more valid benchmarks with relevant details, your contribution will be acknowledged in the next update of the paper's Acknowledgment section.

Come on and join us !!

If you find our work useful, please give us a star. Thank you !!

---

📖 Citation

If you find our work useful, please cite our paper as:

@article{zhang2025large,
  author    = {Zhang, Zicheng and Wang, Junying and Wen, Farong and Guo, Yijin and Zhao, Xiangyu and Fang, Xinyu and Ding, Shengyuan and Jia, Ziheng and Xiao, Jiahao and Shen, Ye and Zheng, Yushuo and Zhu, Xiaorong and Wu, Yalun and Jiao, Ziheng and Sun, Wei and Chen, Zijian and Zhang, Kaiwei and Fu, Kang and Cao, Yuqin and Hu, Ming and Zhou, Yue and Zhou, Xuemei and Cao, Juntai and Zhou, Wei and Cao, Jinyu and Li, Ronghui and Zhou, Donghao and Tian, Yuan and Zhu, Xiangyang and Li, Chunyi and Wu, Haoning and Liu, Xiaohong and He, Junjun and Zhou, Yu and Liu, Hui and Zhang, Lin and Wang, Zesheng and Duan, Huiyu and Zhou, Yingjie and Min, Xiongkuo and Jia, Qi and Zhou, Dongzhan and Zhang, Wenlong and Cao, Jiezhang and Yang, Xue and Yu, Junzhi and Zhang, Songyang and Duan, Haodong and Zhai, Guangtao},
  title     = {Large Multimodal Models Evaluation: A Survey},
  journal   = {SCIENCE CHINA Information Sciences},
  year      = {2025},
  volume    = {},
  pages     = {},
  url       = {https://www.sciengine.com/SCIS/doi/10.1007/s11432-025-4676-4},
  doi       = {https://doi.org/10.1007/s11432-025-4676-4}
}

Table of Contents

• Large Multimodal Models Evaluation: A Survey
  • Contributions
  • 📖 Citation
  • Table of Contents
  • Understanding Evaluation
    • General
      • Adaptability
      • Basic Ability
      • Comprehensive Perception
      • General Knowledge
      • Safety
    • Specialized
      • Math
      • Physics
      • Chemistry
      • Finance
      • Healthcare & Medical Science
      • Code
    • Autonomous Driving
      • Earth Science / Remote Sensing
      • Embodied Tasks
      • AI Agent
  • Generation Evaluation
    • Image
    • Video
    • Audio
    • 3D
  • Leaderboards and Tools

---

Understanding Evaluation

General

Adaptability

Benchmark	Paper	Project Page
LLaVA-Bench	Visual instruction tuning	Github
MIA-Bench	Mia-bench: Towards better instruction following evaluation of multimodal llms	Github
MM-IFEval	MM-IFEngine: Towards Multimodal Instruction Following	Github
VisIT-Bench	VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use	Github
MMDU	MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs	Github
ConvBench	ConvBench: A Multi-Turn Conversation Evaluation Benchmark with Hierarchical Capability for Large Vision-Language Models	Github
SIMMC 2.0	SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations	Github
Mementos	Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences	Github
MUIRBENCH	MUIRBENCH: A Comprehensive Benchmark for Robust Multi-image Understanding	Github
MMIU	MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models	Github
MIRB	Benchmarking Multi-Image Understanding in Vision and Language Models: Perception, Knowledge, Reasoning, and Multi-Hop Reasoning	Github
MIBench	MIBench: Evaluating Multimodal Large Language Models over Multiple Images	Hugging Face
II-Bench	II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models	Github
Mantis	Mantis: Interleaved Multi-Image Instruction Tuning	Github
MileBench	MILEBENCH: Benchmarking MLLMs in Long Context	Github
ReMI	ReMI: A Dataset for Reasoning with Multiple Images	Hugging Face
CODIS	CODIS: Benchmarking Context-Dependent Visual Comprehension for Multimodal Large Language Models	Github
SPARKLES	SPARKLES: UNLOCKING CHATS ACROSS MULTIPLE IMAGES FOR MULTIMODAL INSTRUCTION-FOLLOWING MODELS	Github
MMIE	MMIE: MASSIVE MULTIMODAL INTERLEAVED COMPREHENSION BENCHMARK FOR LARGE VISIONLANGUAGE MODELS	Github
InterleavedBench	Holistic Evaluation for Interleaved Text-and-Image Generation	Hugging Face
OpenING	OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation	Github
HumaniBench	HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation	Github
Herm-Bench	HERM: Benchmarking and Enhancing Multimodal LLMs for Human-Centric Understanding	Github
UNIAA	UNIAA: A Unified Multi-modal Image Aesthetic Assessment Baseline and Benchmark	Github
Humanbeauty	HumanAesExpert: Advancing a Multi-Modality Foundation Model for Human Image Aesthetic Assessment	Github
SocialIQA	SOCIAL IQA: Commonsense Reasoning about Social Interactions	Hugging Face
EmpathicStories	EmpathicStories++: A Multimodal Dataset for Empathy towards Personal Experiences	Dataset Download
Chatbot Arena	Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference	Not available
OpenAssistant Conversations	OpenAssistant Conversations - Democratizing Large Language Model Alignment	Github
HCE	Human-Centric Evaluation for Foundation Models	Github

Basic Ability

Benchmark	Paper	Project Page
NWPU-MOC	NWPU-MOC: A Benchmark for Fine-grained Multi-category Object Counting in Aerial Images	Github
T2V-ComBench	T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation	Github
ConceptMix	ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty	Github
PICD	Can Machines Understand Composition? Dataset and Benchmark for Photographic Image Composition Embedding and Understanding	Github
TextVQA	Towards VQA Models That Can Read	Github
OCR-VQA	OCR-VQA: Visual Question Answering by Reading Text in Images	Dataset download
OCRBench	OCRBENCH: ON THE HIDDEN MYSTERY OF OCR IN LARGE MULTIMODAL MODELS	Github
OCRBench v2	OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning	Github
ASCIIEval	VISUAL PERCEPTION IN TEXT STRINGS	Github
OCRReasoning	OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning	Github
M4-ViteVQA	Towards Video Text Visual Question Answering: Benchmark and Baseline	Github
SEED-Bench-2-Plus	SEED-Bench-2-Plus: Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehension	Github
MMDocBench	MMDOCBENCH: BENCHMARKING LARGE VISIONLANGUAGE MODELS FOR FINE-GRAINED VISUAL DOCUMENT UNDERSTANDING	Github
MMLongBench-Doc	MMLONGBENCH-DOC: Benchmarking Long-context Document Understanding with Visualizations	Github
UDA	UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysis	Github
VisualMRC	VisualMRC: Machine Reading Comprehension on Document Images	Github
DocVQA	DocVQA: A Dataset for VQA on Document Images	Hugging Face
DocGenome	DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models	Github
GDI-Bench	GDI-Bench: A Benchmark for General Document Intelligence with Vision and Reasoning Decoupling	Dataset download
AitW	Android in the Wild: A Large-Scale Dataset for Android Device Control	Github
ScreenSpot	SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents	Github
VisualWebBench	VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?	Github
GUI-WORLD	GUI-WORLD: A VIDEO BENCHMARK AND DATASET FOR MULTIMODAL GUI-ORIENTED UNDERSTANDING	Github
WebUIBench	WebUIBench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in WebUI-to-Code	Github
ScreenQA	ScreenQA: Large-Scale Question-Answer Pairs Over Mobile App Screenshots	Github
ChartQA	ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning	Github
ChartQApro	CHARTQAPRO : A More Diverse and Challenging Benchmark for Chart Question Answering	Github
ComTQA	TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy	Github
TableVQA-Bench	TableVQA-Bench: A Visual Question Answering Benchmark on Multiple Table Domains	Github
CharXiv	CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs	Github
SciFIBench	SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure Interpretation	Github
AI2D-RST	AI2D-RST: A multimodal corpus of 1000 primary school science diagrams	Github
InfoChartQA	InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic Charts	Github
EvoChart-QA	EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding	Github
WikiMixQA	WikiMixQA: A Multimodal Benchmark for Question Answering over Tables and Charts	Github
ChartX	ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning	Github
Q-Bench	Q-BENCH: A BENCHMARK FOR GENERAL-PURPOSE FOUNDATION MODELS ON LOW-LEVEL VISION	Github
A-Bench	A-BENCH: ARE LMMS MASTERS AT EVALUATING AI-GENERATED IMAGES?	Github
MVP-Bench	MVP-Bench: Can Large Vision–Language Models Conduct Multi-level Visual Perception Like Humans?	Github
XLRS-Bench	XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?	Github
HR-Bench	Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models	Github
MME-RealWorld	MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?	Github
V*Bench	V ∗ : Guided Visual Search as a Core Mechanism in Multimodal LLMs	Github
FaceBench	FaceBench: A Multi-View Multi-Level Facial Attribute VQA Dataset for Benchmarking Face Perception MLLMs	Github
MMAFFBench	MMAFFBen: A Multilingual and Multimodal Affective Analysis Benchmark for Evaluating LLMs and VLMs	Github
FABA-Bench	Facial Affective Behavior Analysis with Instruction Tuning	Github
MEMO-Bench	MEMO-Bench: A Multiple Benchmark for Text-to-Image and Multimodal Large Language Models on Human Emotion Analysis	Github
EmoBench	EmoBench: Evaluating the Emotional Intelligence of Large Language Models	Github
EEmo-Bench	EEmo-Bench: A Benchmark for Multi-modal Large Language Models on Image Evoked Emotion Assessment	Github
AesBench	AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception	Github
UNIAA-Bench	UNIAA: A Unified Multi-modal Image Aesthetic Assessment Baseline and Benchmark	Github
ImplictAVE	ImplicitAVE: An Open-Source Dataset and Multimodal LLMs Benchmark for Implicit Attribute Value Extraction	Github
II-Bench	II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models	Hugging Face
CogBench	A Cognitive Evaluation Benchmark of Image Reasoning and Description for Large Vision-Language Models	Github
A4Bench	Affordance Benchmark for MLLMs	Github
MM-SAP	MM-SAP: A Comprehensive Benchmark for Assessing Self-Awareness of Multimodal Large Language Models in Perception	Github
Cambrian-1	Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs	Github
MMUBench	Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models	Not available
MMVP	Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs	Github
MicBench	Towards Open-ended Visual Quality Comparison	Github
CuturalVQA	Benchmarking Vision Language Models for Cultural Understanding	Hugging Face
RefCOCO Family	Modeling Context in Referring ExpressionsGeneration and Comprehension of Unambiguous Object Descriptions	Github Github
Ref-L4	Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal Models	Github
MRES-32M	Unveiling Parts Beyond Objects: Towards Finer-Granularity Referring Expression Segmentation	Github
UrBench	UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios	Github
COUNTS	COUNTS: Benchmarking Object Detectors and Multimodal Large Language Models under Distribution Shifts	Github
MTVQA	MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering	Github
GePBench	GePBench: Evaluating Fundamental Geometric Perception for Multimodal Large Language Models	Not available
SpatialMQA	Can Multimodal Large Language Models Understand Spatial Relations?	Github
SpacialRGPT-Bench	SpatialRGPT: Grounded Spatial Reasoning in Vision-Language Models	Github
CoSpace	CoSpace: Benchmarking Continuous Space Perception Ability for Vision-Language Models	Github
LMM-CompBench	MLLM-COMPBENCH: A Comparative Reasoning Benchmark for Multimodal LLMs	Github
SOK-Bench	SOK-Bench: A Situated Video Reasoning Benchmark with Aligned Open-World Knowledge	Github
GSR-Bench	GSR-BENCH: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs	Not available
What's "up"	What’s “up” with vision-language models? Investigating their struggle with spatial reasoning	Github
Q-Spatial Bench	Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models	Github
AS-V2	The All-Seeing Project V2: Towards General Relation Comprehension of the Open World	Github
Visual CoT	Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning	Github
LogicVista	LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts	Github
VisuLogic	VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models	Github
CoMT	CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Models	Github
PUZZLES	PUZZLES: A Benchmark for Neural Algorithmic Reasoning	Github
LOVA3	LOVA3 : Learning to Visual Question Answering, Asking and Assessment	Github
VLIKEB	VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark	Github
MMKE-Bench	MMKE-BENCH: A MULTIMODAL EDITING BENCHMARK FOR DIVERSE VISUAL KNOWLEDGE	Github
MC-MKE	MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality ConsistencyMIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing	Not available
NegVQA	NegVQA: Can Vision Language Models Understand Negation?	Github
LongBench	LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding	Github
OPOR-BENCH	OPOR-Bench: Evaluating Large Language Models on Online Public Opinion Report Generation	Not available
VRT-Bench	Visual Reasoning Tracer: Object-Level Grounded Reasoning Benchmark	Github

Comprehensive Perception

Benchmark	Paper	Project Page
LVLM-eHub	Lvlm-ehub: A comprehensive evaluation benchmark for large vision-language models.	GitHub
TinyLVLM-eHub	Tinylvlm-ehub: Towards comprehensive and efficient evaluation for large vision-language models.	GitHub
LAMM	Lamm: Language-assisted multi-modal instruction-tuning dataset, framework, and benchmark.	GitHub
MME	Mme: A comprehensive evaluation benchmark for multimodal large language models.	Project Page
MMBench	Mmbench: Is your multi-modal model an all-around player?	GitHub
SEED-Bench series	SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension.	GitHub
MMT-Bench	Mmt-bench: A comprehensive multimodal benchmark for evaluating large vision-language models towards multitask agi.	GitHub
LMMs-Eval	Lmms-eval: Reality check on the evaluation of large multimodal models.	GitHub
MMStar	Are we on the right way for evaluating large vision-language models?	GitHub
NaturalBench	Naturalbench: Evaluating vision-language models on natural adversarial samples.	Project Page
MM-Vet	Mm-vet: Evaluating large multimodal models for integrated capabilities.	GitHub
ChEF	Chef: A comprehensive evaluation framework for standardized assessment of multimodal large language models.	GitHub
Video-MME	Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis.	GitHub
MMBench-Video	Mmbench-video: A long-form multi-shot benchmark for holistic video understanding.	GitHub
MVBench	Mvbench: A comprehensive multi-modal video understanding benchmark.	Hugging Face
LongVideoBench	Longvideobench: A benchmark for long-context interleaved video-language understanding.	GitHub
LVBench	Lvbench: An extreme long video understanding benchmark.	GitHub
MotionBench	Motionbench: Benchmarking and improving fine-grained video motion understanding for vision language models.	GitHub
AudioBench	Audiobench: A universal benchmark for audio large language models.	GitHub
AIR-Bench	Air-bench: Benchmarking large audio-language models via generative comprehension.	GitHub
Dynamic-SUPERB	Dynamic-superb: Towards a dynamic, collaborative, and comprehensive instruction-tuning benchmark for speech.	GitHub
M3DBench	M3dbench: Let's instruct large models with multi-modal 3d prompts.	GitHub
M3D	M3d: Advancing 3d medical image analysis with multi-modal large language models.	GitHub
Space3D-Bench	Space3d-bench: Spatial 3d question answering benchmark.	Project Page

General Knowledge

Benchmark	Paper	Project Page
ScienceQA	Learn to explain: Multimodal reasoning via thought chains for science question answering.	GitHub
CMMU	Cmmu: A benchmark for chinese multi-modal multi-type question understanding and reasoning.	GitHub
Scibench	Scibench: Evaluating college-level scientific problem-solving abilities of large language models.	GitHub
EXAMS-V	Exams-v: A multi-discipline multilingual multi-modal exam benchmark for evaluating vision language models.	Hugging Face
MMMU	Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi.	GitHub
MMMU-Pro	Mmmu-pro: A more robust multi-discipline multimodal understanding benchmark.	Hugging Face
HLE	Humanity's last exam.	Project Page
CURIE	Curie: Evaluating llms on multitask scientific long context understanding and reasoning.	GitHub
SFE	Scientists' first exam: Probing cognitive abilities of mllm via perception, understanding, and reasoning.	Hugging Face
MMIE	Mmie: Massive multimodal interleaved comprehension benchmark for large vision-language models.	GitHub
MDK12-Bench	Mdk12-bench: A multi-discipline benchmark for evaluating reasoning in multimodal large language models.	GitHub
EESE	The ever-evolving science exam.	Project Page
Q-Mirror	Q-Mirror: Unlocking the Multi-Modal Potential of Scientific Text-Only QA Pairs	GitHub

Safety

Benchmark	Paper	Project Page
Unicorn	How many unicorns are in this image? a safety evaluation benchmark for vision llms.	GitHub
JailbreakV-28K	Jailbreakv-28k: A benchmark for assessing the robustness of multimodal large language models against jailbreak attacks.	GitHub
MM-SafetyBench	Mm-safetybench: A benchmark for safety evaluation of multimodal large language models.	GitHub
AVIBench	Avibench: Towards evaluating the robustness of large vision-language model on adversarial visual-instructions.	GitHub
MMJ-Bench	MMJ-Bench: A Comprehensive Study on Jailbreak Attacks and Defenses for Vision Language Models.	GitHub
USB	Usb: A comprehensive and unified safety evaluation benchmark for multimodal large language models.	GitHub
MLLMGuard	Mllmguard: A multi-dimensional safety evaluation suite for multimodal large language models.	GitHub
SafeBench	Safebench: A safety evaluation framework for multimodal large language models.	GitHub
MemeSafetyBench	Are vision-language models safe in the wild? a meme-based benchmark study.	Hugging Face
UnsafeBench	Unsafebench: Benchmarking image safety classifiers on real-world and ai-generated images.	Not available
POPE	Evaluating object hallucination in large vision-language models.	GitHub
M-HalDetect	Detecting and preventing hallucinations in large vision language models.	Not available
Hal-Eval	Hal-eval: A universal and fine-grained hallucination evaluation framework for large vision language models.	GitHub
Hallu-pi	Hallu-pi: Evaluating hallucination in multi-modal large language models within perturbed inputs.	Not available
BEAF	Beaf: Observing before-after changes to evaluate hallucination in vision-language models.	GitHub
HallusionBench	Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models.	Project Page
AutoHallusion	Autohallusion: Automatic generation of hallucination benchmarks for vision-language models.	GitHub
MultiTrust	Benchmarking trustworthiness of multimodal large language models: A comprehensive study.	GitHub
MMDT	Mmdt: Decoding the trustworthiness and safety of multimodal foundation models.	GitHub
Text2VLM	Text2vlm: Adapting text-only datasets to evaluate alignment training in visual language models.	Not available
MOSSBench	Mossbench: Is your multimodal language model oversensitive to safe queries?	GitHub
CulturalVQA	Benchmarking vision language models for cultural understanding.	Project Page
ModScan	Modscan: Measuring stereotypical bias in large vision-language models from vision and language modalities.	GitHub
FMBench	Fmbench: Benchmarking fairness in multimodal large language models on medical tasks.	Not available
FairMedFM	Fairmedfm: Fairness benchmarking for medical imaging foundation models.	GitHub
FairCLIP	Fair-clip: Harnessing fairness in vision-language learning.	GitHub
DoxingBench	Doxing via the lens: Revealing privacy leakage in image geolocation for agentic multi-modal large reasoning model.	Hugging Face
PrivQA	Can language models be instructed to protect personal information?	Not available
SHIELD	Shield: An evaluation benchmark for face spoofing and forgery detection with multimodal large language models.	GitHub
ExtremeAIGC	Extremeaigc: Benchmarking lmm vulnerability to ai-generated extremist content.	Not available

Specialized

Math

Benchmark	Paper	Project Page
MathVista	Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts.	GitHub
PolyMATH	Polymath: A challenging multi-modal mathematical reasoning benchmark.	Project Page
MATH-Vision	Measuring multimodal mathematical reasoning with math-vision dataset.	Project Page
Olympiad-Bench	Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems.	GitHub
PolyMath	Polymath: Evaluating mathematical reasoning in multilingual contexts.	GitHub
Math-Verse	Mathverse: Does your multi-modal llm truly see the diagrams in visual math problems?	GitHub
WE-MATH	We-math: Does your large multimodal model achieve human-like mathematical reasoning?	GitHub
MathScape	Mathscape: Evaluating mllms in multimodal math scenarios through a hierarchical benchmark.	Github
CMM-Math	Cmm-math: A chinese multimodal math dataset to evaluate and enhance the mathematics reasoning of large multimodal models.	Hugging Face
MV-MATH	Mv-math: Evaluating multimodal math reasoning in multi-visual contexts.	GitHub

Physics

Benchmark	Paper	Project Page
ScienceQA	Learn to explain: Multimodal reasoning via thought chains for science question answering.	GitHub
TQA	Are you smarter than a sixth grader? textbook question answering for multimodal machine comprehension.	Not available
AI2D	A diagram is worth a dozen images.	Project Page
MM-PhyQA	Mm-phyqa: Multimodal physics question answering with multi-image cot prompting.	Not available
PhysUniBench	Physunibench: An undergraduate-level physics reasoning benchmark for multimodal models.	Project Page
PhysicsArena	Physicsarena: The first multimodal physics reasoning benchmark exploring variable, process, and solution dimensions.	Hugging Face
SeePhys	Seephys: Does seeing help thinking? benchmarking vision-based physics reasoning.	GitHub
PhysReason	Physreason: A comprehensive benchmark towards physics-based reasoning.	Hugging Face
OlympiadBench	Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems.	GitHub
SceMQA	Scemqa: A scientific college entrance level multimodal question answering benchmark.	GitHub
PACS	Pacs: A dataset for physical audiovisual commonsense reasoning.	GitHub
GRASP	GRASP: A novel benchmark for evaluating language grounding and situated physics understanding in multimodal language models.	GitHub
CausalVQA	Causalvqa: A physically grounded causal reasoning benchmark for video models.	GitHub
LiveXiv	Livexiv a multi-modal live benchmark based on arxiv papers content.	GitHub
VideoScience-Bench	Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench.	GitHub

Chemistry

Benchmark	Paper	Project Page
SMILES	Smiles, a chemical language and information system. 1. introduction to methodology and encoding rules.	Project Page
ChEBI-20	Text2mol: Cross-modal molecule retrieval with natural language queries.	GitHub
ChemBench	Chemllm: A chemical large language model.	GitHub
SELFIES	Self-referencing embedded strings (selfies): A 100% robust molecular string representation.	GitHub
InChI	Inchi, the iupac international chemical identifier.	Project Page
MolX	Molx: Enhancing large language models for molecular learning with a multi-modal extension.	Not available
GiT-Mol	Git-mol: A multi-modal large language model for molecular science with graph, image, and text.	GitHub
Instruct-Mol	Instructmol: Multi-modal integration for building a versatile and reliable molecular assistant in drug discovery.	GitHub
ChEBI-20-MM	A quantitative analysis of knowledge-learning preferences in large language models in molecular science.	GitHub
MMCR-Bench	Chemvlm: Exploring the power of multimodal large language models in chemistry area.	GitHub
MACBench	Probing the limitations of multimodal language models for chemistry and materials research.	GitHub
3D-MoLM	Towards 3d molecule-text interpretation in language models.	GitHub
M3-20M	M3-20m: A large-scale multi-modal molecule dataset for ai-driven drug design and discovery.	GitHub
MassSpecGym	Massspecgym: A benchmark for the discovery and identification of molecules.	GitHub
MolPuzzle	Can llms solve molecule puzzles? a multimodal benchmark for molecular structure elucidation.	GitHub

Finance

Benchmark	Paper	Project Page
FinMME	FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation	Github
FAMMA	FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering	Project Page
MME-Finance	MME-Finance: A Multimodal Finance Benchmark for Expert-level Understanding and Reasoning	Project Page
MultiFinBen	MultiFinBen: A Comprehensive Multimodal Financial Benchmark	Github
CFBenchmark-MM	CFBenchmark-MM: A Comprehensive Multimodal Financial Benchmark	Github
FinMMR	FinMMR: Multimodal Financial Reasoning Benchmark	Github
Fin-Fact	Fin-Fact: Financial Fact Checking Dataset	Github
FCMR	FCMR: Financial Multimodal Reasoning
FinTral	FinTral: Financial Translation and Analysis	Github
Open-FinLLMs	Open-FinLLMs: Open Financial Large Language Models	Hugging Face
FinGAIA	FinGAIA: Financial AI Assistant	Github

Healthcare & Medical Science

Benchmark	Paper	Project Page
VQA-RAD	VQA-RAD: Visual Question Answering Radiology Dataset	Project Page
PathVQA	PathVQA: Pathology Visual Question Answering	Github
RP3D-DiagDS	RP3D-DiagDS: 3D Medical Diagnosis Dataset	Project Page
PubMedQA	PubMedQA: Medical Question Answering Dataset	Project Page
HealthBench	HealthBench: Medical AI Benchmark	Project Page
GMAI-MMBench	GMAI-MMBench: General Medical AI Multimodal Benchmark	Project Page
OpenMM-Medical	OpenMM-Medical: Open Medical Multimodal Model	Github
Genomics-Long-Range	Genomics-Long-Range: Long-Range Genomic Benchmark	Hugging Face
Genome-Bench	Genome-Bench: Comprehensive Genomics Benchmark	Hugging Face
MedAgentsBench	MedAgentsBench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning	Github
MedQ-Bench	MedQ-Bench: Evaluating and Exploring Medical Image Quality Assessment Abilities in MLLMs	Github

Code

Benchmark	Paper	Project Page
Design2Code	Design2Code: From Design Mockups to Code	Project Page
Web2Code	Web2Code: Web-to-Code Generation	Project Page
Plot2Code	Plot2Code: From Charts to Code	Hugging Face
ChartMimic	ChartMimic: Chart Understanding and Generation	Project Page
HumanEval-V	HumanEval-V: Visual Code Generation Benchmark	Project Page
Code-Vision	Code-Vision: Visual Code Understanding	Github
SWE-bench Multi-modal	SWE-bench Multi-modal: Software Engineering Benchmark	Project Page
MMCode	MMCode: Multimodal Code Generation	Github
M²Eval	M²Eval: Multimodal Code Evaluation	Github
BigDocs-Bench	BigDocs-Bench: Large Document Understanding	Project Page
BigDocs-Bench	Bigdocs: An open dataset for training multimodal models on document and code tasks.	GitHub

Autonomous Driving

Benchmark	Paper	Project Page
Rank2Tell	Rank2Tell: Ranking-based Visual Storytelling	Project Page
DRAMA	DRAMA: Dynamic Risk Assessment for Autonomous Vehicles	Project Page
NuScenes-QA	NuScenes-QA: Autonomous Driving Question Answering	Github
LingoQA	LingoQA: Driving Language Understanding	Github
V2V-LLM	V2V-LLM: Vehicle-to-Vehicle Communication	Project Page
MAPLM-QA	MAPLM: Real-World Large-Scale Vision-Language Benchmark for Map and Traffic	Github
SURDS	SURDS: Autonomous Driving Dataset	Github
AD2-Bench	AD2-Bench: Autonomous Driving Benchmark
DriveAction	DriveAction: Driving Action Recognition	Hugging Face
DriveLMM-01	DriveLMM-01: Driving Language Model	Github
DriveVLM	DriveVLM: Vision-Language Model for Driving	Project Page
RoboTron-Sim	RoboTron-Sim: Robot Simulation Platform	Project Page
IDKB	IDKB: Intelligent Driving Knowledge Base	Project Page
VLADBench	VLADBench: Vision-Language-Action Driving Benchmark	Github
DriVQA	DriVQA: Driving Visual Question Answering
ADGV-Bench	Are AI-Generated Driving Videos Ready for Autonomous Driving? A Diagnostic Evaluation Framework	Not available

Earth Science / Remote Sensing

Benchmark	Paper	Project Page
GEOBench-VLM	GEOBench-VLM: Geospatial Vision-Language Model Benchmark	Project Page
ClimaQA	ClimaQA: Climate Question Answering	Github
ClimateBERT	ClimateBERT: Climate Language Model	Project Page
WeatherQA	WeatherQA: Weather Question Answering	Github
OceanBench	OceanBench: Ocean Data Analysis Benchmark	Project Page
OmniEarth-Bench	OmniEarth-Bench: Comprehensive Earth Observation	Hugging Face
MSEarth	MSEarth: Multi-Scale Earth Observation	Github
EarthSE	EarthSE: Earth System Evaluation	Hugging Face
RSICD	RSICD: Remote Sensing Image Captioning Dataset	Github
NWPU-Captions	NWPU-Captions: Remote Sensing Image Descriptions	Github
RSVQA-HRBEN/LRBEN	RSVQA: Remote Sensing Visual Question Answering	Project Page
DIOR-RSVG	DIOR-RSVG: Remote Sensing Visual Grounding	Github
VRSBench	VRSBench: Visual Remote Sensing Benchmark	Project Page
LRS-VQA	LRS-VQA: Large-scale Remote Sensing VQA	Github
GeoChat-Bench	GeoChat-Bench: Geospatial Conversation Benchmark	Github
XLRS-Bench	XLRS-Bench: Cross-Lingual Remote Sensing	Project Page
RSIEval	RSIEval: Remote Sensing Image Evaluation	Github
UrBench	UrBench: Urban Remote Sensing Benchmark	Project Page
CHOICE	CHOICE: Comprehensive Remote Sensing Benchmark	Github
SARChat-Bench-2M	SARChat-Bench-2M: SAR Image Understanding	Github
LHRS-Bench	LHRS-Bench: Large-scale High-Resolution Remote Sensing	Github
FIT-RSFG	FIT-RSFG: Remote Sensing Fine-Grained Recognition	Github
VLEO-Bench	VLEO-Bench: Very Low Earth Orbit Benchmark	Project Page
NAIP-OSM	NAIP-OSM: Aerial Imagery and Map Alignment	Project Page

Embodied Tasks

Benchmark	Paper	Project Page
Embodied Questioning Answering (EQA)	EXPRESS-Bench: Embodied Question Answering	Project Page
R2R (Room-to-Room)	R2R: Room-to-Room Navigation	Github
Reverie	Reverie: Remote Embodied Visual Referring Expression	Project Page
Alfred	Alfred: A Benchmark for Interpreting Grounded Instructions	Github
Calvin	Calvin: Long-Horizon Language-Conditioned Robot Learning	Github
EPIC-KITCHENS	EPIC-KITCHENS: Large Scale Dataset in First Person Vision	Project Page
Ego4D	Ego4D: Around the World in 3,000 Hours	Project Page
EMQA	EMQA: Ego-centric Multimodal Question Answering	Github
SQA3D	SQA3D: Situated Question Answering in 3D Scenes	Project Page
Open-EQA	Open-EQA: Open-Vocabulary Embodied Question Answering	Project Page
HM-EQA	HM-EQA: Hierarchical Multi-modal Embodied QA	Project Page
MOTIF	MOTIF: Multimodal Object-Text Interaction Framework	Github
EgoTaskQA	EgoTaskQA: Understanding Tasks in Egocentric Videos	Project Page
EmbodiedScan	EmbodiedScan: Holistic Multi-Modal 3D Perception	Project Page
RH20T-P	RH20T-P: Robotic Manipulation Dataset	Project Page
EXPRESS-Bench	EXPRESS-Bench: Embodied Question Answering	Github
EmbodiedEval	EmbodiedEval: Embodied AI Evaluation	Project Page
Embodied Bench	Embodied Bench: Comprehensive Embodied AI Evaluation	Project Page
VLABench	VLABench: Vision-Language-Action Benchmark	Project Page
EWMBench	EWMBench: Embodied World Model Benchmark	Github
NeurIPS 2025 Embodied Agent Interface Challenge	NeurIPS 2025 Embodied Agent Interface Challenge	Project Page
SEER-Bench	Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration	Not available
ReMindView-Bench	Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective	Github

AI Agent

Benchmark	Paper	Project Page
Self-rag	Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection	GitHub
AMEM	A-MEM: Agentic Memory for LLM Agents	GitHub

Generation Evaluation

Image

Benchmark	Paper	Project Page
DiffusionDB	DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models	GitHub
HPD、HPD v2、HPS	Human Preference Score: Better Aligning Text-to-Image Models with Human Preference	GitHub
ImageReward、ImageReward/ReFL	ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation	GitHub
Pick-A-Pic、PickScore	Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation	GitHub
AGIQA-1K	A Perceptual Quality Assessment Exploration for AIGC Images	GitHub
AGIQA-3K	AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment	GitHub
AIGCIQA2023	AIGCIQA2023: A Large-scale Image Quality Assessment Database for AI Generated Images: from the Perspectives of Quality, Authenticity and Correspondence	Hugging Face
AGIN、JOINT	Exploring the Naturalness of AI-Generated Images	GitHub
AIGIQA-20K	AIGIQA-20K: A Large Database for AI-Generated Image Quality Assessment	Hugging Face
AIGCOIQA2024	AIGCOIQA2024: Perceptual Quality Assessment of AI Generated Omnidirectional Images	GitHub
CMC-Bench	CMC-Bench: Towards a New Paradigm of Visual Signal Compression	GitHub
PKU-I2IQA、NR/FR-AIGCIQA	PKU-I2IQA: An Image-to-Image Quality Assessment Database for AI Generated Images	GitHub
SeeTRUE	What You See is What You Read? Improving Text-Image Alignment Evaluation	GitHub
AIGCIQA2023+、MINT-IQA	Quality Assessment for AI Generated Images with Instruction Tuning	GitHub
Q-Eval-100K、Q-Eval Score	Q-Eval-100K: Evaluating Visual Quality and Alignment Level for Text-to-Vision Content	GitHub
Measuring the Quality of Text-to-Video Model Outputs	Measuring the Quality of Text-to-Video Model Outputs: Metrics and Dataset	Dataset Download
EvalCrafter	EvalCrafter: Benchmarking and Evaluating Large Video Generation Models	GitHub
FETV	FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation	GitHub
VBench	VBench: Comprehensive Benchmark Suite for Video Generative Models	GitHub
T2VQA-DB	Subjective-Aligned Dataset and Metric for Text-to-Video Quality	GitHub
GAIA	GAIA: Rethinking Action Quality Assessment for AI-Generated Videos	GitHub
AIGVQA-DB、AIGV-Assessor	AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM	GitHub
AIGVE-60K、LOVE	LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation	GitHub
Human-AGVQA-DB、GHVQ	Human-Activity AGV Quality Assessment: A Benchmark Dataset and an Objective Evaluation Metric	GitHub
TDVE-DB、TDVE-Assessor	TDVE-Assessor: Benchmarking and Evaluating the Quality of Text-Driven Video Editing with LMMs	GitHub
AGAVQA-3K、AGAV-Rater	AGAV-Rater: Adapting Large Multimodal Model for AI-Generated Audio-Visual Quality Assessment	GitHub
Qwen-ALLD	Audio Large Language Models Can Be Descriptive Speech Quality Evaluators	Hugging Face
BASE-TTS	BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data	Audio samples of BASE-TTS
ATT	Audio Turing Test: Benchmarking the Human-likeness of Large Language Model-based Text-to-Speech Systems in Chinese	Hugging Face
TTSDS2	TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech Systems	Website
MATE-3D、LGVQ	Benchmarking and Learning Multi-Dimensional Quality Evaluator for Text-to-3D Generation	GitHub
3DGCQA	3DGCQA: A Quality Assessment Database for 3D AI-Generated Contents	GitHub
AIGC-T23DAQA	Multi-Dimensional Quality Assessment for Text-to-3D Assets: Dataset and Model	GitHub
SI23DCQA	SI23DCQA: Perceptual Quality Assessment of Single Image-to-3D Content	GitHub
3DGS-IEval-15K	3DGS-IEval-15K: A Large-scale Image Quality Evaluation Database for 3D Gaussian-Splatting	GitHub
Inception Score (IS)	Improved Techniques for Training GANs	GitHub
FVD	Towards Accurate Generative Models of Video: A New Metric & Challenges	GitHub
VQAScore	Evaluating Text-to-Visual Generation with Image-to-Text Generation	GitHub
NTIRE 2024 AIGC QA	NTIRE 2024 Quality Assessment of AI-Generated Content Challenge	Website
Q-Bench	Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision	GitHub
Q-instruct	Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models	GitHub
Q-align	Q-ALIGN: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels	GitHub
Q-boost	Q-Boost: On Visual Quality Assessment Ability of Low-level Multi-Modality Foundation Models	Project Page
Co-Instruct	Towards Open-ended Visual Quality Comparison	Hugging Face
DepictQA	Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models	GitHub
M3-AGIQA	M3-AGIQA: Multimodal, Multi-Round, Multi-Aspect AI-Generated Image Quality Assessment	GitHub
Q-Refine	Q-Refine: A Perceptual Quality Refiner for AI-Generated Image	GitHub
AGIQA	Large Multi-modality Model Assisted AI-Generated Image Quality Assessment	GitHub
SF-IQA	SF-IQA: Quality and Similarity Integration for AI Generated Image Quality Assessment	GitHub
SC-AGIQA	Text-Visual Semantic Constrained AI-Generated Image Quality Assessment	GitHub
TSP-MGS	AI-Generated Image Quality Assessment Based on Task-Specific Prompt and Multi-Granularity Similarity	Not available
MoE-AGIQA	MoE-AGIQA: Mixture-of-Experts Boosted Visual Perception-Driven and Semantic-Aware Quality Assessment for AI-Generated Images	GitHub
AMFF-Net	Adaptive Mixed-Scale Feature Fusion Network for Blind AI-Generated Image Quality Assessment	GitHub
PSCR	PSCR: Patches Sampling-based Contrastive Regression for AIGC Image Quality Assessment	GitHub
TIER	TIER: Text-Image Encoder-based Regression for AIGC Image Quality Assessment	GitHub
IPCE	AIGC Image Quality Assessment via Image-Prompt Correspondence	GitHub
RISEBench	Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing	GitHub
GoT	GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing	GitHub
SmartEdit	SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models	GitHub
WISE	WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation	GitHub
KRIS-Bench	KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models	GitHub
CoT-editing	Enhancing Image Editing with Chain-of-Thought Reasoning and Multimodal Large Language Models	Not available
GUIZoom-Bench	Zoom in, Click out: Unlocking and Evaluating the Potential of Zooming for GUI Grounding	Github
MICo-Bench	MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition	Github
CS-Bench	START: Spatial and Textual Learning for Chart Understanding	Not available
IF-Bench	IF-Bench: Benchmarking and Enhancing MLLMs for Infrared Images with Generative Visual Prompting	Github ｜

Video

Benchmark	Paper	Project Page
LMM-VQA	LMM-VQA: Advancing Video Quality Assessment with Large Multimodal Models	GitHub
FineVQ	FineVQ: Fine-Grained User Generated Content Video Quality Assessment	GitHub
VQA^2	VQA2 : Visual Question Answering for Video Quality Assessment	GitHub
Omni-VQA	Scaling-up Perceptual Video Quality Assessment	Not available
LMM-PVQA	Breaking Annotation Barriers: Generalized Video Quality Assessment via Ranking-based Self-Supervision	GitHub
Compare2Score paradigm	Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare	GitHub
VQ-Insight	VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning	GitHub
Who is a Better Talker	Who is a Better Talker: Subjective and Objective Quality Assessment for AI-Generated Talking Heads	GitHub
THQA	THQA: A Perceptual Quality Assessment Database for Talking Heads	GitHub
Who is a Better Imitator	Who is a Better Imitator: Subjective and Objective Quality Assessment of Animated Humans	GitHub
MI3S	MI3S: A multimodal large language model assisted quality assessment framework for AI-generated talking heads	Not available
An Implementation of Multimodal Fusion System	An Implementation of Multimodal Fusion System for Intelligent Digital Human Generation	GitHub
RULER-Bench	RULER-Bench: Probing Rule-based Reasoning Abilities of Next-level Video Generation Models for Vision Foundation Intelligence	GitHub
PAI-Bench	PAI-Bench: A Comprehensive Benchmark For Physical AI	Github
Tri-Bench	Tri-Bench: Stress-Testing VLM Reliability on Spatial Reasoning under Camera Tilt and Object Interference	Github
OpenVE-Bench	OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing	Github
RVE-Bench	ReViSE: Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning	Github

Audio

Benchmark	Paper	Project Page
MOSNet	MOSNet: Deep Learning-based Objective Assessment for Voice Conversion	GitHub
MOSA-Net+	A Study on Incorporating Whisper for Robust Speech Assessment	Hugging Face
MOSLight	MOSLight: A Lightweight Data-Efficient System for Non-Intrusive Speech Quality Assessment	Not available
MBNet	MBNet: MOS Prediction for Synthesized Speech with Mean-Bias Network	GitHub
DeePMOS	DeePMOS: Deep Posterior Mean-Opinion-Score of Speech	GitHub
LDNet	LDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speech	GitHub
ADTMOS	ADTMOS – Synthesized Speech Quality Assessment Based on Audio Distortion Tokens	GitHub
UAMOS	Uncertainty-Aware Mean Opinion Score Prediction	Not available
Audiobox Aesthetics	Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound	GitHub
HighRateMOS	HighRateMOS: Sampling-Rate Aware Modeling for Speech Quality Assessment	Not available
ALLMs-as-Judges	Audio-Aware Large Language Models as Judges for Speaking Styles	Hugging Face
SALMONN	SALMONN: Towards Generic Hearing Abilities for Large Language Models	GitHub
Qwen-Audio	Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models	GitHub
Qwen2- Audio	Qwen2-Audio Technical Report	GitHub
natural language quality descriptions	Enabling Auditory Large Language Models for Automatic Speech Quality Evaluation	GitHub
QualiSpeech	QualiSpeech: A Speech Quality Assessment Dataset with Natural Language Reasoning and Descriptions	Hugging Face
DiscreteEval	Evaluating Text-to-Speech Synthesis from a Large Discrete Token-based Speech Language Model	GitHub
EmergentTTS-Eval	EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judge	GitHub
InstructTTSEval	INSTRUCTTTSEVAL: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems	GitHub
Mos-Bench	MOS-Bench: Benchmarking Generalization Abilities of Subjective Speech Quality Assessment Models	Hugging Face
SH-Bench	Protecting Bystander Privacy via Selective Hearing in LALMs	Huggingface
LISN-Bench	LISN: Language-Instructed Social Navigation with VLM-based Controller Modulating	Github

3D

Benchmark	Paper	Project Page
NR-3DQA	No-Reference Quality Assessment for 3D Colored Point Cloud and Mesh Models	GitHub
MM-PCQA	MM-PCQA: Multi-Modal Learning for No-reference Point Cloud Quality Assessment	GitHub
GT23D-Bench	GT23D-Bench: A Comprehensive General Text-to-3D Generation Benchmark	GitHub
NeRF-NQA	NeRF-NQA: No-Reference Quality Assessment for Scenes Generated by NeRF and Neural View Synthesis Methods	GitHub
Explicit-NeRF-QA	Explicit-NeRF-QA: A Quality Assessment Database for Explicit NeRF Model Compression	GitHub
NeRF-QA	NeRF-QA: Neural Radiance Fields Quality Assessment Database	GitHub
NVS-QA	NeRF View Synthesis: Subjective Quality Assessment and Objective Metrics Evaluation	GitHub
GSQA	GS-QA: Comprehensive Quality Assessment Benchmark for Gaussian Splatting View Synthesis	GitHub
GPT-4V Evaluator	GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation	GitHub
Eval3D	Eval3D: Interpretable and Fine-grained Evaluation for 3D Generation	GitHub
3DGen-Bench	3DGen-Bench: Comprehensive Benchmark Suite for 3D Generative Models	GitHub
LMM-PCQA	LMM-PCQA: Assisting Point Cloud Quality Assessment with LMM	GitHub

Leaderboards and Tools

Platform / Benchmark	Paper	Project Page
LMMs-Eval	LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models	GitHub
GenAI-Arena	Genai arena: An open evaluation platform for generative models	Hugging Face
OpenCompass		GitHub
Epoch AI’s Benchmarking Hub		Website
Artificial Analysis		Website
Scale’s SEAL Leaderboards		Website
FlagEval	FlagEvalMM: A Flexible Framework for Comprehensive Multimodal Model Evaluation	Website
AGI-Eval	AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models	Website
ReLE		Website
VLMEvalKit、OpenVLM Leaderboard	VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models	GitHub
HELM	Holistic Evaluation of Language Models	Project Page
LiveBench	LiveBench: A Challenging, Contamination-Limited LLM Benchmark	Project Page
SuperCLUE	SuperCLUE: A Comprehensive Chinese Large Language Model Benchmark	Website
AIBench	AIbench: Towards Trustworthy Evaluation Under the 45 Law	Website
FutureX	FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction	Github