HyperAIHyperAI
HomeConsoleDocsNewsPapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Command Palette

Search for a command to run...

AI SOTA Benchmarks

Latest AI model performance metrics, GPU benchmarks, and cutting-edge papers

Categories

Browse tasks by category

Computer Vision

921 tasks

Image Classification

166 benchmarks, 2,881 models, 865 papers

Semantic Segmentation

149 benchmarks, 1,875 models, 696 papers

Object Detection

122 benchmarks, 1,010 models, 380 papers

Few-Shot Image Classification

90 benchmarks, 911 models, 157 papers

Image Generation

90 benchmarks, 823 models, 274 papers

Natural Language Processing

428 tasks

Question Answering

149 benchmarks, 1,782 models, 447 papers

Text Classification

85 benchmarks, 313 models, 108 papers

Machine Translation

83 benchmarks, 437 models, 160 papers

Named Entity Recognition (NER)

77 benchmarks, 441 models, 159 papers

Text Generation

71 benchmarks, 50 models, 28 papers

Medical

152 tasks

Medical Image Segmentation

48 benchmarks, 318 models, 119 papers

Drug Discovery

28 benchmarks, 96 models, 37 papers

Sleep Stage Detection

16 benchmarks, 55 models, 15 papers

Within-Session ERP

15 benchmarks, 135 models, 1 papers

Text-to-Image Generation

13 benchmarks, 128 models, 64 papers

Miscellaneous

152 tasks

Image Super-Resolution

68 benchmarks, 744 models, 144 papers

Recommendation Systems

55 benchmarks, 248 models, 91 papers

Click-Through Rate Prediction

20 benchmarks, 126 models, 47 papers

Molecular Property Prediction

18 benchmarks, 224 models, 36 papers

Age Estimation

16 benchmarks, 109 models, 30 papers

Methodology

98 tasks

Object Detection

122 benchmarks, 1,010 models, 380 papers

Anomaly Detection

76 benchmarks, 656 models, 253 papers

Classification

71 benchmarks, 132 models, 66 papers

Domain Adaptation

58 benchmarks, 387 models, 155 papers

Unsupervised Domain Adaptation

41 benchmarks, 288 models, 111 papers

Time Series

59 tasks

Time Series Forecasting

86 benchmarks, 537 models, 75 papers

Time Series Classification

52 benchmarks, 231 models, 30 papers

Traffic Prediction

33 benchmarks, 192 models, 61 papers

Pose Estimation

31 benchmarks, 232 models, 123 papers

GLinear

19 benchmarks, 19 models, 1 papers

Speech

56 tasks

Speech Recognition

148 benchmarks, 398 models, 135 papers

Speech Separation

19 benchmarks, 127 models, 46 papers

Speaker Diarization

15 benchmarks, 40 models, 10 papers

Speech Emotion Recognition

15 benchmarks, 45 models, 31 papers

Speech Enhancement

14 benchmarks, 110 models, 63 papers

Graphs

52 tasks

Node Classification

127 benchmarks, 1,751 models, 235 papers

Link Prediction

80 benchmarks, 497 models, 165 papers

Graph Classification

72 benchmarks, 791 models, 149 papers

Image Super-Resolution

68 benchmarks, 744 models, 144 papers

Graph Regression

17 benchmarks, 234 models, 81 papers

Reasoning

46 tasks

Common Sense Reasoning

24 benchmarks, 397 models, 81 papers

Zero-Shot Video Question Answer

16 benchmarks, 221 models, 65 papers

Math Word Problem Solving

13 benchmarks, 243 models, 70 papers

Visual Reasoning

12 benchmarks, 191 models, 45 papers

Logical Reasoning

10 benchmarks, 65 models, 7 papers

Audio

38 tasks

Audio Classification

26 benchmarks, 191 models, 91 papers

Beat Tracking

15 benchmarks, 15 models, 1 papers

Downbeat Tracking

13 benchmarks, 13 models, 1 papers

Few-Shot Audio Classification

10 benchmarks, 67 models, 2 papers

Bandwidth Extension

6 benchmarks, 6 models, 2 papers

Robots

30 tasks

Semantic Segmentation

149 benchmarks, 1,875 models, 696 papers

Fraud Detection

12 benchmarks, 45 models, 18 papers

DeepFake Detection

11 benchmarks, 30 models, 19 papers

Omniverse Isaac Gym

6 benchmarks, 12 models, 2 papers

Visual Navigation

6 benchmarks, 40 models, 19 papers

Computer Code

28 tasks

Semantic Segmentation

149 benchmarks, 1,875 models, 696 papers

Code Generation

26 benchmarks, 245 models, 79 papers

Deblurring

16 benchmarks, 197 models, 67 papers

Text-To-SQL

10 benchmarks, 85 models, 37 papers

Source Code Summarization

9 benchmarks, 11 models, 4 papers

Knowledge

23 tasks

Math Word Problem Solving

13 benchmarks, 243 models, 70 papers

Text-to-Image Generation

13 benchmarks, 128 models, 64 papers

Entity Alignment

10 benchmarks, 97 models, 25 papers

Multi-modal Entity Alignment

8 benchmarks, 62 models, 6 papers

Document Summarization

7 benchmarks, 50 models, 25 papers

Playing Games

18 tasks

Continuous Control

73 benchmarks, 116 models, 13 papers

Image Super-Resolution

68 benchmarks, 744 models, 144 papers

Atari Games

64 benchmarks, 2,518 models, 68 papers

OpenAI Gym

17 benchmarks, 45 models, 9 papers

SMAC+

16 benchmarks, 133 models, 10 papers

Music

17 tasks

DeepFake Detection

11 benchmarks, 30 models, 19 papers

Music Transcription

6 benchmarks, 31 models, 14 papers

Audio Super-Resolution

4 benchmarks, 14 models, 8 papers

Cover song identification

4 benchmarks, 21 models, 8 papers

Music Auto-Tagging

4 benchmarks, 7 models, 4 papers

Adversarial

11 tasks

Open-Domain Question Answering

15 benchmarks, 109 models, 39 papers

Face Detection

13 benchmarks, 139 models, 41 papers

Handwritten Text Recognition

13 benchmarks, 47 models, 19 papers

Adversarial Defense

10 benchmarks, 28 models, 15 papers

Adversarial Robustness

7 benchmarks, 33 models, 6 papers