HyperAI
Command Palette
Search for a command to run...
Model Optimization / NAS
Automatically searching for optimal neural architectures (NAS) and compressing models through pruning, quantization, and knowledge distillation.
Leaderboard
100 models total
Benchmarks
ImageNet
NAT-M4
CIFAR-100
DensE
ImageNet-1K
CIFAR-10
TAS-pruned ResNet-110
PIQA
BoolQ
Hella-Swag
ARC-e
ARC-c
MMLU
Wino Grande
GSM-8K
GQA
TextVQA
MM MU
RTE
POPE
CIFAR10
ScienceQA
Vizwiz
MM B
OBQA
Tiny-ImageNet
SST-2
OCR-Bench
VQA-v2
Arc-Easy
AI2D
SQA
MM-Bench
MNIST
Arc-Challenge
MMB-CN
COPA
WSC
ChartQA
MATH
SVHN
WG
MM-Star
HumanEval
Open-BookQA
SEED
CSQA
Euro SAT
Doc-VQA
RE-SISC45
MathQA
MM-Vet
DTD
SUN-397
MNLI
MRPC
ScienceQA-IMG
WIC
C.B.
MATH-500
SVAMP
VQAText
VTAB-1K
ImageNet-100
MME
SEED-Bench
HeSw
Race-h
Fashion-MNIST
HS
MBPP
QNLI
GOLD (T5-base)
CIFAR-10-DVS
ImageNette
LongBench
Cars
HSwag
ImageWoof
BBH
CALTECH-101
CUB-200-2011
IMDB
ModelNet-40
Pets
STL-10
Flowers
Flowers-102
RULER
SIQA
six downstream tasks
MMLU-Pro
RealWorldQA
RWQA
SciQ
WNLI
CIFAR-100 LT
FGV-CAircraft
Hallusion Bench
M2S-GL
S2S-CN
S2S-EU
Strategy-QA
ASDiv
Common-senseQA
Food-101
Math-Vista
MAWPS
OK-VQA
Video-MME
A-OKVQA
BLINK
CoLA
DVS-Gesture
GPQA-Diamond
GTSRB
ImageNet-16-120
Live-CodeBench
MMLU-STEM
MMMU-Pro
MR
MultiRC
Oxford-IIIT-Pets
SEED2+
SQA-IMG
WinoG
ARC
CMMLU
ImageNet - ResNet 50 - 90% sparsity
Feather
InfoVQA
NAS-Bench-201
OCR-VQA
QQP
SEED-IMG
Sen12Flood
TDIUC
BigMath level 4
BigMath level 5
Camelyon
Celeb-DF
Clevr-Count
Clevr-Dist
DMLab
dSpr-Loc
dSpr-Ori
FF++
FMoW
HumanEval+
ImageNet-A
ImageNet-LT
ImageNet-V2
KITTI-Dist
LRA Image
MMB-EN
MQAR
NATS-Bench Topology, CIFAR-10
NATS-Bench Topology, CIFAR-100
NATS-Bench Topology, ImageNet16-120
Olympiad-Bench
Pubmed
ReCoRD
RefCOCO
Retinopathy
Sat
sNORB-Azim
SQA^I
SQuAD
SuperGPQA
TabMWP
TREC
TREC-6
Wino
Amazon Polarity
ARC-challenging
BLiMP
Cal. Wildfires
Citeseer
Cora
GLUE
ImageNet-R
Kinetics-400
LAMBADA
SNLI
Aircraft
BIG-bench
Celeb-A
Chaoyang
CIFAR-10 WRN-28-10 - 200 Epochs
Adam (eps-adjusted)
CIFAR-100 WRN-28-10 - 200 Epochs
AvaGrad
DVS-CIFAR10
FinanceQA
Flower-102
ImageNet-C
ImageNet-Sketch
LAMA
LeetCode
LexGLUE
MedM-CQA
Photo
R52
R8
RefCOCO-g
RefCOCO+
ScanObjectNN
sNORB-Ele
Stanford-Cars
TruthfulQA
VizWiz-VQA
XNLI
AIME-24
Ape-clean
CLIP benchmark
CoQA
GPQA
IFEval
InfiniteBench
IS
LogiQA
Math23k
MMMU-Val
Office-Home
Oxford Flowers-102
RACE
SEEDB
VQAT
AIME-2024
Amazon Counterfactual
Amazon Reviews
Arxiv
AV-MNIST
Banking-77
Belebele
Birdsnap
CIFAR - 2 × 5
CIFAR-10 ResNet-18 - 200 Epochs
SGD - cosine LR schedule
CIFAR-100(C)
CIFAR-26-45
CIFAR-50-74
Comp
Cover Type
CS
Emotion
GSM8K-CoT
HELMET
Ionosphere
LongVideo Bench
Massive Intent
Massive Scenario
Med QA
MMB^dev
MMLU-Flan-Cot-Fewshot
MMMU^test
MSR-VTT
MSVD
MTOPDomain
MTOPIIntent
NAS-Bench-101
nids
PACS
Phys.
Songs
SS T
Tiny-ImageNet-LT
Tiny-Inet
Toxic Conversations
Tweet Sentiment Extraction
UCM
urls
Vision-Language Tasks
VisWiz
VLCS
Waterbirds-100
ActivityNet-QA
AG-News
AGI Eval
AI2Diagram
AIME 2024-2025
AIME-25
ALFRED
AMC-23
ARC challenged
BB-sub
Biased MNIST
CIFAR-10-LT
CLEVR-C
Coin Flip
D&D
Ego-Schema
Flickr-30K
GPQA-D
Hallusion
HMDB-51
IEdit
ImageIDC
ImageNet-200
ImageNet-Real
IMDB-B
InfographicVQA
Iris
Junyi
Kuzushiji-MNIST
Lam.
LAMBADA-OpenAI
LCC
LongBench-e
MLVU
MM-AU
MMCoQA
MMMUv
MSRVT-QA
MSVD-QA
MultiPL-E
MUTAG
MV-Bench
NExT-QA
NLU
OI
PAWS-X
PMC-VQA
Proteins
PTADisc
PTC-MR
Repobench-P
SciQA-IMG
SEED-Bench (Image)
SEED-I
SLT-10
Something-Something (V2)
SQL
ST
STD
Story
T-VQA
TGIF
TN
top quark tagging
TransNAS-Bench-101
TransNAS-Bench-101-Micro
ViGGO
WC-VQA
WebSRC
X-StoryCloze
XCOPA
Yelp
20News
ActivityNet
AFHQ
AIME-120
AMC
ANLI1
Bank Notes
Breast-Cancer
C.M.
C3
CIFAR
CINIC
CK
CMExam
Coauthor-CS
Coauthor Phy
COCO
SSD ResNet50 V1 FPN 640x640
COCO-2017
COMPAS
Compressed Meta (2025)
Computer
Corrupted CIFAR-10
CQA
CSQA Tasks
Domain-Net
DriveLM
Drop
e-SNLI
ELEC2
EPIC-KITCHENS-100
ESC-50
F-mnist
FICO
FiQA_SA
GPQA-Diamond-MC
GSM8K-PLUS
HAM
HellaS
House-16H
HTRU2
IL
ImageNet-22k
ImageNet-S
ImageNet-Woof
iNat-19
LLaVA^W
LRA
MIT-Indoor67
MME-RW
MMLongBench-Doc
ModelNet
Multi-Color MNIST
N-MNIST
NA Birds
Needle-in-a-Haystack
ObjectNet
OCRB
Ogbn-Arxiv
Ogbn-products
OmniBench
Oxford Flowers
Oxford-pets
Permuted MNIST
Pima Indians
Pima-Diabetes
PL
PM
Pneumonia MNIST
PoL
Polychromatic Meta (2025)
PRE
QASPER
RULER-4K
S-MNIST
SciQA
SciTail
Seeds
Sentiment140
Sequential MNIST
ShapeNet
SingleEq
Spambase
SST-5
Stanford-Dogs
Subj
Trivia QA
UCF-101
Union
unknown
Visual HayStack
VQA^2
VSI-Bench
Yelp Review
20-Newsgroups
Academic Papers
adult
AIME
amazon-photos
AQUA-RAT
AudioMNIST
babyLM
Bank marketing
BBH-test
BERT
C-Eval
C10.1
C10.2
Cats-and-Dogs
CBT
CESM
CHID
CIFAR-10(C)
CINIC-10
CMNLI
Copying memory
CREMA-D
DNACorpus
Dolly
DriveLMM-o1
EgoGesture
EgoPlan
Enwik9
gauss
Gender Pronoun Resolution (GP)
GSM8K Chat
Hella
IllusionVQA
Image
ImageFruit
ImageMeow
ImageNet-10
ImageNet-B
ImageNet-D
ImageNet-E
ImageNet-Subset
ImageSquawk
ImageYellow
Imbalanced CIFAR-100
in-house dataset
Indirect Object Identification (IOI)
industry status monitoring dataset
Instruct HumanEval
IOI
KBQA
Law
LJ Speech
LLaVA-B
Long-Range Arena
m-brick-kiln
m-eurosat
m-so2sat
MagnifierBench
Mathematicas
Medical
Mhealth
Mini Speech Commands
mLAMA
MMBench-CN
MMLU Chat
MMT-Bench
Movie Plots
MRCR
Multi-Fashion
Multi-MNIST
multi-topic
MVoxCeleb
NATS-Bench Size, CIFAR-10
NATS-Bench Size, CIFAR-100
NATS-Bench Size, ImageNet16-120
News Articles
NTU RGB-D
NumGLUE
NUS
Objaverse
PAMAP2
PARAREL
Path
PATH-X
psMNIST
Reuters3
Reuters5
Rice
RSI-CB256
RSVQA-HRBEN
S-NI
sCIFAR (grayscale)
ScreenSpot
SEED-Image
SeedBench (video)
Self-inst
Shakespeare
ShapeNet-55
Silesia
Song Lyrics
STL
STS-B
TCGA-BRCA
TestImages
TextCAPS
Tiny-ImageNet-200
Tiny-ImageNet-C
Unist
Unseen Tasks
UR-FUNNY
UVG
V* Bench
VC100
VCR
VGGSound
Vicuna
Video
VQA 2.0
VT200
Wildfires
XLSum English
YouCook2
YouTubeFace