HyperAI
Command Palette
Search for a command to run...
Video Understanding
Comprehending video content holistically, including action recognition, temporal localization, video question answering, and event detection.
Leaderboard
100 models total
Benchmarks
Video-MME
LongVideo Bench
MLVU
Ego-Schema
MV-Bench
NExT-QA
LV-Bench
QVHighlights
UMT (w/ audio + PT ASR Cpations)
ActivityNet-QA
MSVD-QA
MSR-VTT-QA
Charades-STA
TempCompass
Video-MMMU
Perception-Test
THUMOS-14
STAR
VSI-Bench
NExT-GQA
Kinetics-400
ActivityNet
FS-QAT
Coin
ActivityNet-Captions
Vid2Seq
Streaming Bench
TACoS
CG-DETR
Intent-QA
MMVU
OVO-Bench
UCF-101
ActivityNet-1.3
GQA
TGIF-QA
HMDB-51
POPE
Something-Something (V2)
VNBench
VQA-v2
AI2D
Vid-Halluc
AGQA
CVQA
EventHallusion
NLVR2 Dev
ViLT-B/32
MM B
NLVR2 Test
BEiT-3
ShanghaiTech Weakly Supervised
TimeScope
Video-Holmes
VMME
MM-Bench
RVS-Ego
RVS-Movie
TextVQA
BLINK
K400
MF2
RealWorldQA
University-1652
LPN
FineAction
HAAN
MLVU-Test
UCF-Crime
Video-MME (long)
YouCook2
E2vidD6-MASSalign-BiD
ActivityNet-v1.3
Doc-VQA
ImageNet-1K
MovieNet
ScienceQA
TVSum
FlashVTG
UBnormal
OCC-WS
VideoEspresso
Charades
ChartQA
FineVidBench
Kinetics-700
MM MU
MME
SQA
VideoNIAH
Vizwiz
WildVideo
YouTube Highlights
CG-DETR
AVHaystacks-50
AVHaystacks-Full
Breakfast
CinePile
Kinetics-600
Math-Vista
MM-Vet
MMB-CN
MMIU
QAEgo4D
SEED
TGIF
TVBench
TVQA
VideoHallucer
VidSTG
Vinoground
VQAText
ActivityNet-RTL
CG-Bench
CG-Bench-mini
Cholec 80
LoViT
Ego-ST Bench
Ego4D
EgoLifeQA
EGTEA
ImageNet VID 2015
Mantis
Moments in Time V1
SciQA
SS-V2
StreamBench
UBI-Fights
GMM
VCR-Bench
ActNet-QA
Arc-Challenge
Cross-Task
EgoPlan
EgoSchema (subset)
Ekman6
EPIC-KITCHENS-100
eSports Sensors Dataset
SVM
HACS
HeiChole Benchmark
Hella-Swag
LongBench
LongTVQA
LongTVQA+
LSDBench
MIRB
MM-Star
MMLU
MotionBench
MSR-Action3D
MSR-VTT
MSVD
NLVR2
Open-BookQA
TOMATO
VideoSIAH-Eval
VLEP
VSR
LXMERT
XD-Violence
50-Salads
AGQA-Decomp
ANet-Caption
BDD-100K
Causal-VidQA
CLEVRER-MC
Ego4D-NLQ
FutureBench
HCSTVG-v2
HumanML3D
ST-MLP
LVU
MathVerse
MovieChat-1K
Muir-Bench
nuScenes
Penn Action
PercepTest
SoccerNet-v2
SSv2-MC
TemporalBench
UnAV-100
VAGU
Video-MME(no subtitle)
VideoMME w/ sub.
VideoMME w/o sub.
ViTT
VStream-QA
3D-assisted Dialogue
ActivityNet-VRL
ActivityQA
ALFRED
ANet-QA
Animal Kingdom
AoTBench
Diving-48
Drive&Act
EasyCom
Ego-R1 Bench
EgoMQ
EGOPOINTVQA
EgoTempo
EK-100 CLS
EK-100 MIR
ELV-Halluc
EMMA
HC-STVG
HCSTVG-v1
How2QA
Image Edit Instruction
K700
KIT Motion-Language
MLP+GRU
LAV-DF
LLaVA-Interleave Bench
LLaVA^W
LongVideoBench_val
M3CoT
Mapillary Vistas
MATH-Vision
MathVerse-mv
MISAW
MLVU-dev
MM-IQ
MM-Math
MMMU-mv
MMMU-Pro
MMSI
MovieChat
MUIR
Multi-image VQA
Multi-THUMOS
MUSIC-AVQA
MV-MATH
NBA
nuScenes VQA
OCR-Bench
OnlineMMSI
OpenEQA
Perception
PitVQA
Puzzle
Q-Bench
ROADWork
ScanQA
SceneBench
ScienceQA-Image
SciVerse-mv
SEED-Bench-R1
SEED-Image
Shot2Story20K
Ours
SHREC'17
Sports-QA
SportsMoments
Spot the Difference
SSV2-QA
Task Decomposition
Text-rich VQA
TextQA
TVQA+
VIDAL-QA
VideoChatGPT
VideoMME (w/o sub.)
VIDHAL
Visual Story Telling
VisWiz
Volleyball
VQAT
WebVid-QA
YouTube-HL
Active Memories Benchmark (AMB)
ActivityForensics
ActivityNet-Caption
ANC-S
ANet-Captions
AV-Counting
AV-Odyssey
ave.
AVSD
CALTECH-101
CCD
DSTA
CIFAR-100
CREMA-D
VAVL
Daily-Omni
DynPose-100K
E.T. Bench
E.T. Bench (Subset)
Ego-Exo4D
Ego4D Goal-Step
Ego4D Moment Query
EgoProceL
EgoTaskQA
EgoTaskVQA
EventDrive
FALCON-Bench
Friends-MMC
FunQA
GraSP
MuST
HippoVlog
InfographicVQA
IntentBench
iVQA
Kinetics
L-VidBench
LangAuto
LLama-Vid
LongVB
Mantis-Eval
MGSV-EC
MiTv1
MMA-52
MMR-V
Movie QA
MultiClip-Bench
ODV-Bench
OK-VQA
OMEBench
OmniBench
Panda
PKU Multi-Modality Dataset
QVHighlight
RexTime
RivaBench
SheepActivity
ShotBench
SQA-IMG
SQA^I
STAR-sub
Streamo-Bench
TAU-106K
Toyota Smarthome Untrimmed
TSL300
TSU
TVQA-Long
VidChapters-7M
Video-MME(wo sub)
VideoHallu
ViTIB
VLN-QA
Vript-RR
Worldsense
1 Megapixel Automotive Detection Dataset
20BN-Jester
A -> H
A-F
A-T
ActionBench
Active Memory Benchmark
ActivityNet-MR
ActivityNet-RF
ALL
ANet
AVA
AVL, AVS
AVQA
BBC
BDD100K val
FM-Net
Bench2Drive
BestShot Benchmark
Breakfast Actions
C-GQA
C-Sports
CATE
CATER
Charade-STA
Charades-CD-OOD
Charades-CG
Charades-RF
CholecT45
CIFAR-10
CLEVRER
CLIP Classification Benchmark
CLIP Retrieval Benchmark (Flickr)
CMU
CMU-MOSEI
Comma.ai
Country-211
CUEBENCH
CUVA
CVS
DTD
DynSuperCLEVR
EgoExoLearn
EgoMCQ
EgoMe
EgoMem
EgoMemoria
EgoNormia
EgoPER
EgoYC2
EGTEA Gaze+
EK-100
Env-QA
ERQA
ESC-50
Euro SAT
EV2-Bench
Event-Chat
EventBench
Explicit Omni-SILA Dataset
F-A
F-T
FavorBench
FER2013
FGV-CAircraft
FineDiving-QA
Flowers-102
Food-101
GPS
GTEA
GTSRB
H-A
H2O
HAICBench
Hallusion Bench
HD-EPIC++
HDD
HLVid
HMDB51-VISPR
Hollywood Extended
HT-Step
HTM-Align
Human-P&C
HVU
IKEA-ASM
ImageNet-Adv.
ImageNet-Ren.
ImageNet-Ske.
ImageNet-V2
Implicit Omni-SILA Dataset
interlaken_00_b
interlaken_01_a
JHMDB51-21
K-600
Kinetics700-QA
LiViBench
LLaVA-Bench-in-the-wild
LLP
LongVideo-Reason
LongVideo-Reason-eval
LSMDC
LVB
LVR
M-VAE dataset
MA-Bench
MECD
VGCM
MM-AU
MMSI-Bench
MMT-Bench
MMVU(mc)
MNIST
MomentDETR
MOSCATO-EGTEA
MoVid-Bench-Motion
MoVid-Bench-Video
MSAD
MSRVT
MUSES
Music
MUSIC-AVQA-Real
MUSIC-QA
NAP
NaVQA
NCAA
Nexar
NExT-VMR
NextQA-MC
NextQA-valset
NGSIM
TraPHic
NIV
Nymeria
ObjectNet
OC-NaVQA
OmniGround
OmniSpatial
Open X-Embodiment
Our Benchmark
OV-SD
PALADIN
PCAM
Pets
PKU-MMD-CS
PLM-VideoBench
ProReady-QA
ProstaTD
QV-M2
R-AVST
R4D-Bench
RARP
RE-SISC45
RefAVA
Rendered-SST2
RES
RoadSocial-QA
RoboX-VQA
SA
Sat
ScienceQA-IMG
SEED-Bench
Sensor
SFX-Moment
Sports-3K-QA
SSv2-Small
ST-Align
ST-Align benchmark
Stanford-Cars
STAR-bench-QA
Sth-V2
STI-Bench
STL-10
STVD-PVCD
STVG
SUN-397
SurgPub-Video
SUTD
Swing
T-A
T-F
Temporal Audio Grounding
TemporalBench (S)
THQA-10K
THUMOS' 14
FS-QAT
thun_01_a
thun_01_b
Timeline Speech Summarization
TRAF
TraPHic
TSU-CS
TVSeries
UAV-SVG
UCF101-24
UCF101-VISPR
Udacity
FM-Net
UFVideo-Bench
unknown
VAST-Bench
VCG-Bench
VDC
VEU-Bench
VidDiffBench
VideoEval-Pro
VideoMathQA
VideoMME (S)
VideoMME_short
VideoMME_w/sub.
VideoRefer-Bench-Q
VideoVista
VidTAB
VITATECS
VIUBench
VLM4D-real
VMB
VOC 2007
VRBench
VS-Ego
VS-Movie
VSGR
VSTI-Bench
VSTREAM-QA-EGO
VTV150K
WiFi-HAR
YJMob100K@B
YJMob100K@C
ST-MoE-BERT
YJMob100K@D
zurich_city_12_a
zurich_city_14_c
zurich_city_15_a