Active Benchmarks by Domain

Browse verified, actively-maintained benchmarks by problem domain. These are the recommended datasets for evaluating your models.

Finding the right benchmark

1

Pick your domain

What type of problem? (vision, language, audio, etc.)

2

Find your task

What specific problem are you solving?

3

Choose dataset

Which benchmark fits your use case?

4

Compare results

How does your model stack up?

Browse by problem domain

Computer Vision

Building systems that understand images and video? Find benchmarks for recognition, detection, segmentation, and document analysis tasks.

27 tasks199 datasets1778 results
Optical Character RecognitionScene Text DetectionScene Text RecognitionDocument Layout Analysis+23 more

Reasoning

Testing if your model can think logically? Benchmark math problem solving, commonsense understanding, and multi-step reasoning capabilities.

5 tasks19 datasets158 results
Mathematical ReasoningCommonsense ReasoningMulti-step ReasoningLogical Reasoning+1 more

Computer Code

Developing AI coding assistants? Test code generation, completion, translation, bug detection, and repair capabilities.

6 tasks13 datasets136 results
Code GenerationCode TranslationBug DetectionCode Completion+2 more

Natural Language Processing

Processing and understanding text? Evaluate your models on language understanding, generation, translation, and information extraction benchmarks.

14 tasks17 datasets83 results
Text SummarizationText ClassificationQuestion AnsweringText Ranking+10 more

Time Series

Predicting future trends or detecting anomalies? Benchmark forecasting accuracy and pattern recognition in sequential data.

4 tasks8 datasets82 results
Time Series ForecastingTabular ClassificationTabular RegressionTime Series Classification

Medical

Building healthcare AI? Find benchmarks for medical imaging, disease diagnosis, clinical text processing, and drug discovery.

4 tasks13 datasets71 results
Disease ClassificationMedical Image SegmentationClinical NLPDrug Discovery

Agentic AI

Measuring autonomous AI capabilities? METR benchmarks track time horizon, multi-step reasoning, and sustained task performance - key metrics for AGI progress.

6 tasks6 datasets42 results
SWE-benchWeb & Desktop AgentsHCASTTime Horizon+2 more

Multimodal

Combining vision and language? Evaluate image captioning, visual QA, text-to-image generation, and cross-modal retrieval models.

10 tasks23 datasets37 results
Visual Question AnsweringImage CaptioningVideo UnderstandingAny-to-Any+6 more

Speech

Working with voice and audio? Evaluate speech-to-text accuracy, voice synthesis quality, and speaker identification performance.

5 tasks6 datasets31 results
Speech RecognitionText-to-SpeechVoice CloningSpeaker Verification+1 more

Industrial Inspection

Building quality control systems? Benchmark anomaly detection, defect classification, and automated visual inspection for manufacturing.

4 tasks7 datasets27 results
Anomaly DetectionWeld InspectionSteel Defect DetectionSurface Defect Detection

Reinforcement Learning

Training agents to make decisions? Benchmark your policies on game playing, continuous control, and offline learning tasks.

3 tasks2 datasets18 results
Continuous ControlAtari GamesOffline RL

Graphs

Working with network data? Test graph learning models on node classification, link prediction, and molecular property tasks.

4 tasks3 datasets6 results
Node ClassificationGraph ClassificationLink PredictionMolecular Property Prediction

Audio

Processing general audio signals? Test your models on sound classification, event detection, music analysis, and source separation.

7 tasks8 datasets0 results
Voice Activity DetectionAudio CaptioningAudio ClassificationAudio-to-Audio+3 more

Methodology

Improving learning efficiency? Test self-supervised, few-shot, transfer, and continual learning approaches.

4 tasks0 datasets0 results
Continual LearningFew-Shot LearningSelf-Supervised LearningTransfer Learning

Robots

Building robotic systems? Find benchmarks for manipulation, navigation, and simulation-to-reality transfer.

4 tasks2 datasets0 results
Robot ManipulationRobot NavigationRoboticsSim-to-Real Transfer

Adversarial

Need to test model robustness? Benchmark resilience against adversarial attacks and evaluate defense mechanisms.

2 tasks0 datasets0 results
Adversarial AttacksAdversarial Robustness

Knowledge Base

Building knowledge systems? Evaluate graph completion, relation extraction, and entity linking performance.

3 tasks0 datasets0 results
Entity LinkingKnowledge Graph CompletionRelation Extraction

17

Research Areas

112

Tasks

326

Datasets

2469

Benchmark Results

Browse OntologyVote on Benchmarks (188)Saturated & LegacyPWC Archive