HyperAI
Command Palette
Search for a command to run...
الاستدلال الحدسي
تقييم قدرة النموذج على تطبيق المعرفة اليومية والحس السليم للإجابة عن الأسئلة واستخلاص الاستنتاجات.
لوحة الصدارة
100 نماذج بالمجموع
مقاييس الأداء
WinoGrande
PIQA
BoolQ
HellaSwag
ARC-c
ARC-e
OBQA
SIQA
GSM8K
ARC-Challenge
CommonsenseQA
SVAMP
ARC-easy
OpenBookQA
AQuA
MMLU
CSQA
LAMBADA
MATH
StrategyQA
MAWPS
ReCoRD
SocialIQa
ARC
MultiArith
RTE
AddSub
TruthfulQA
MRPC
MMLU-PRO
SciQ
PARus
RuCoS
RWSD
SST-2
arcc
arce
LOGIQA
Drop
MMLU-Redux
SingleEq
HellaS.
ScienceQA
WinoG.
AVReasonBench
PubMedQA
WNLI
MATH500
MNLI
Race
GSM8K-MC
MMBench
MMStar
MULTIPUN
BBH
Commonsense Reasoning
CosmosQA
HallusionBench
GQA
HS
TriviaQA
WG
BioASQ
Hella
ProcessBank
QNLI
Wino
XHOPREASON
NExT-QA
ToMbench
M3CoT
SciQA
AIME'25
ARC Challenge
ARC Easy
BIG-bench (Causal Judgment)
BIG-bench (Date Understanding)
BIG-bench (Disambiguation QA)
FANToM
GPQA
NQ
QQP
SingEq
SNLI-VE val
EVE-ROI*
SQA
SQuAD
StoryCloze
WiC
A-OKVQA
BBH-EN
BBH-ZH
BIG-bench (Sports Understanding)
Commonsense170k
CruxEval
KorBench
LC-O
LiveBench
M³UCD
MMLU Pro
MMLU-STEM
QASC
QBQA
REBUS
GPT-4V
ScienceQA + ARC-Challenge
SNLI-VE test
OFA
TextVQA
V* Bench
WG-M
WG-S
ZebraGrid
BLINK
COPA
CREAK
CSQA2
GLUE
HotpotQA
MCTest
MMToM-QA
MuSR
ProntoQA
Social IQa
VSR
AGI
ANLI
BIG-Bench Hard
CLEVRER
CrisisMMD
GPQA Main
GSM-Plus
HumanEval
IntentQA
MedQA-zh
POPE
PopQA
SimpleTom
SWDE
VideoMME
VQAv2
1DC
BigToM
Chem
Event2Mind test
EA-VQ-VAE
FDA
Hi-ToM
Intent-QA
MA
MBPP
MCEval8K
MIR
MIRBENCH
MUIRBench
Phy
RULER
SST2
ToMi
TwoHop
VizWiz
WorldValuesBench
WSC
ancient Egyptian
Andersen tales
apartment (seen)
big-bench
Orca 2-13B
BIG-bench (Winowhy)
Bingo
CoBRa
Combined
Community Alignment
CSQA-2
CSQA-COT1000
GD-VCR
Human
GQA-OOD
GridToM
HaloQuest
KoBALT-Hard
KoBEST-General
MATH-V
GPT4V
medieval castle
Mini-ARC
MMLU-DE
MMMU
MultiRC
MuSiQue
NumGLUE
OCR-VQA
outer space
PACS-Material
PACS-QA
RealToxicityPrompts
ToxiGen
TruthfulQA-DE
Visual Abstractions Benchmark
VQA-CP v2
wild west
Wino.
WinoG
Winogrd
XSum
3DSRBench
ACRE
AGIEval-Math
AIME2025
AQUA-RAT
ARC (Easy)
arith
BIG-bench (Known Unknowns)
PaLM-540B (few-shot, k=5)
billsum
Bongard-LOGO
ChartQA
CNN-DM
COCO-Spatial
Combined Data
combined dataset
CV-Bench
Date Understanding
Falling Tower
Hella-Swag
ImageNet
LMB
LongBench
M-NIAH
MathVista
MedMCQA
MedQA
MMLU-Medical
MMSU
Modular Arithmetic
Parity
PittAds
RealWorldQA
StimuliQA
TVQA
VisWiz
VQA-v2
VTAB1k
What's Up
AG News
ARC-Gen
Belebele
BIG-bench (Logical Sequence)
Chinchilla-70B (few-shot, k=5)
CANDLE500
Causal-VidQA
CB
CLE
CLEVR
CLEVR-Ref
COCO_one
COCO_two
COMMON2SENSE
Commonsense-170K
Controlled_A
Controlled_B
cross-event dataset
CulturalBench
Deductive Reasoning
DocMSU-PLUS
e-SNLI-VE
EgoToM
EmbSpatial
EmoSet
Emotion6
Geographical QA
GlobalCultureQA
HelaS
HellaS
Math10K
MCNC public dataset
MIntRec2.0
MMBench-DEV
MME-CoT
MME-RealWorld-Lite
MMLU-ST
MMMLU
Multi-Illumination Event-Instruction Benchmark
Natural Questions
OCRBench
Oogiri-GO
OpenToM
Physical IQA
PLASMA
POPE-adversarial
RefCOCOg
ScienceQA-IMG
SEED-Image
SpatialBench
SpatialMQA
SpinBench
SQA-IMG
SQuAD-C
SSRBENCH
SuperGLUE
TabMWP
TODAY
V-Star
VG_one
VG_two
Visual Commonsense Reasoning
VRUBench
WebEmo
Winoground
2WikiMQA
ACE
ACL
AI
AI2D
algopuzzlevqa
GPT-4
ARC_eu
AST
ATIS
Banking77
BasqueGLUE
benchmarks
Bird
BL2MP
C-Eval
Camera
Car
ChartBench
CharXiv
CIFAR100
CLadder 1.5
CLINC150
ClothoAQA
CNN/DM
COCOSPATIAL
CODAH
BERT-LARGE
Colored Objects
COMFORT VI
COMFORT#
CommonsenseQA 2.0
CosmosReason1-Bench
CREHate
CRPE
CSQA→OBQA
CSQA→QASC
CTRC
CUBS
CulturalVQA
CultureAtlas
DICE-D
Dog
DTD
e-SNLI
EgoPlanBench2
EuroSAT
EusExams
EusProficiency
EusReading
EusTrivia
EvoChart
FBT
FCMR
FGVC
Flower
fr-grammar
fr-vocab
FRT
GSM8K-Rev
GTSRB
Hallusion Bench
HellaSwag_eu
HEval.
HID-Chart
HR-4K
HR-8K
HRBENCH
HT
IEMOCAP
IEMOCAP-DA
IFEval
IFVL.
ImageNet-1k
INCLUDE
InfoSeek
LLaVA-Bench (In-the-Wild)
Logical Deduction
LRA
MaQA.
MatchIntel
MathQA
MathVision
MCNC original dataset
MELD-DA
MIntRec
MM-Bench
MM-Vet
MMAU
MMBench-Chinese
MMBench-EN
MMLU_eu
MMMU-Pro
MMSI
MMVet
MMVP
MUIR
Multi-domain Deductive Reasoning
Multimodal-RewardBench
MultiNews
MVBench
MyVLM
NIAH-MK
NIAH-MQ
NS
NuScenes-MQA
NuScenes-QA
OBQA→CSQA
OK-VQA
OpenQA
Penguin
PerVA
Phone
PhyCritic-Bench
PHYSICLEAR
PlotQA
PST
PsychGenerator
PubMed
QASC→CSQA
QASC→OBQA
Qasper
QuaRel
QuaRTz
Recipe-MPR
RefCOCO
RefCOCO+
RESISC45
Restaurant
Reverse Curse
RS
RULER-CWE
RULER-Hotpot
Ruozhiba
S-Cifar10
S-Cifar100
S-NIAH
ScienceVQA
SCT
SD
SD-QA
SEED-Bench
SEEDBENCH2PLUS
SemEval 2020
SemEval 2021
SIT
SNIPS
Social-IQ
SSC
SST
StanfordCars
SUN397
SVHN
TallyQA
TreeBench
TruthfulQA 1
TruthfulQA 2
TVK
ULogic
UniVaR
UOT
V*
VCR (Q-A) dev
VCR (Q-A) test
VCR (Q-AR) dev
VCR (Q-AR) test
PEVL
VCR (QA-R) dev
VCR (QA-R) test
Video-MME
VL-RewardBench
VLM2
VQA^T
VQAT
VRef
VSI
VTAB
VTAB-1k
VTK
Winogrande_eu
WSC273
X-StoryCloze
Yo'LLaVA