Categories
Companies
Research
Sign in
Join
Loading the SOTA2 catalog…
SOTA2
Research
Papers
Benchmarks
Datasets
Tasks
SOTA2 Research
Discover SOTA papers with code
SOTA by domain
LLM
Computer Vision
Speech & Audio
Image Generation
View all
SOTA by task
Image Classification
Semantic Segmentation
Object Detection
Question Answering
View all
SOTA by dataset
ImageNet
ADE20K
COCO
Kinetics
View all
Trending benchmarks
rFVD: 8.6
Video Reconstruction on UCF-101 performance trend
Video Reconstruction on UCF-101
Updated 4mo ago
mIoU: 68.64
Semantic Segmentation on ADE20K performance trend
Semantic Segmentation on ADE20K
Updated 4mo ago
Delta Threshold Accuracy (1.25): 73.5
Video Depth Estimation on Sintel performance trend
Video Depth Estimation on Sintel
Updated 4mo ago
Delta 1 Acc: 98.5
Monocular Depth Estimation on NYU v2 performance trend
Monocular Depth Estimation on NYU v2
Updated 4mo ago
ATE: 0.061
Camera Pose Estimation on Sintel performance trend
Camera Pose Estimation on Sintel
Updated 4mo ago
Overall Score: 75
Video Understanding on Video-MME without subtitles performance trend
Video Understanding on Video-MME without subtitles
Updated 4mo ago
M-Avg: 84.3
Long Video Understanding on MLVU performance trend
Long Video Understanding on MLVU
Updated 4mo ago
Accuracy: 100.3
Video Understanding on MVBench (test) performance trend
Video Understanding on MVBench (test)
Updated 4mo ago
Accuracy: 84.5
Video Question Answering on NExT-QA Multi-choice performance trend
Video Question Answering on NExT-QA Multi-choice
Updated 4mo ago
Abs Rel: 0.049
Monocular Depth Estimation on NYU v2 (test) performance trend
Monocular Depth Estimation on NYU v2 (test)
Updated 4mo ago
Accuracy: 96.21
Mathematical Reasoning on GSM8k (Accuracy) performance trend
Mathematical Reasoning on GSM8k (Accuracy)
Updated 4mo ago
Accuracy: 85
Mathematical Reasoning on Countdown performance trend
Mathematical Reasoning on Countdown
Updated 4mo ago
Overall Accuracy: 90.5
Point Tracking on TAP-Vid Kinetics performance trend
Point Tracking on TAP-Vid Kinetics
Updated 4mo ago
Accuracy: 94.42
Object Hallucination Evaluation on POPE performance trend
Object Hallucination Evaluation on POPE
Updated 4mo ago
Pass@1: 100
Code Generation on HumanEval (test) performance trend
Code Generation on HumanEval (test)
Updated 4mo ago
Pass@1: 95.1
Code Generation on MBPP (test) performance trend
Code Generation on MBPP (test)
Updated 4mo ago
Accuracy: 80.2
Mathematical Reasoning on MathVista mini (test) performance trend
Mathematical Reasoning on MathVista mini (test)
Updated 4mo ago
Accuracy: 80.2
Visual Question Answering on RealworldQA performance trend
Visual Question Answering on RealworldQA
Updated 4mo ago
Accuracy: 81.9
Visual Question Answering on GQA performance trend
Visual Question Answering on GQA
Updated 4mo ago
Accuracy: 84.2
Multi-discipline Multimodal Understanding on MMMU performance trend
Multi-discipline Multimodal Understanding on MMMU
Updated 4mo ago