Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark
Y CombinatorBacked by Y Combinator

Discover SOTA papers with code

SOTA by domains

SOTA by tasks

SOTA by datasets

Trending benchmarks

rFVD: 8.6

Video Reconstruction on UCF-101

Updated 1d agomIoU: 68.64

Semantic Segmentation on ADE20K

Updated 1d agoDelta Threshold Accuracy (1.25): 73.5

Video Depth Estimation on Sintel

Updated 1d agoDelta 1 Acc: 98.5

Monocular Depth Estimation on NYU v2

Updated 1d agoATE: 0.061

Camera Pose Estimation on Sintel

Updated 1d agoOverall Score: 75

Video Understanding on Video-MME without subtitles

Updated 1d agoM-Avg: 84.3

Long Video Understanding on MLVU

Updated 1d agoAccuracy: 100.3

Video Understanding on MVBench (test)

Updated 1d agoAccuracy: 84.5

Video Question Answering on NExT-QA Multi-choice

Updated 1d agoAbs Rel: 0.049

Monocular Depth Estimation on NYU v2 (test)

Updated 1d agoAccuracy: 96.21

Mathematical Reasoning on GSM8k (Accuracy)

Updated 1d agoAccuracy: 85

Mathematical Reasoning on Countdown

Updated 1d agoOverall Accuracy: 90.5

Point Tracking on TAP-Vid Kinetics

Updated 1d agoAccuracy: 94.42

Object Hallucination Evaluation on POPE

Updated 1d agoPass@1: 100

Code Generation on HumanEval (test)

Updated 1d agoPass@1: 95.1

Code Generation on MBPP (test)

Updated 1d agoAccuracy: 80.2

Mathematical Reasoning on MathVista mini (test)

Updated 1d agoAccuracy: 80.2

Visual Question Answering on RealworldQA

Updated 1d agoAccuracy: 81.9

Visual Question Answering on GQA

Updated 1d agoAccuracy: 84.2

Multi-discipline Multimodal Understanding on MMMU

Updated 1d ago