HyperAIHyperAI

Command Palette

Search for a command to run...

QA

Answering natural language questions by extracting or generating answers from given context or knowledge bases.

Leaderboard

100 models total

Benchmarks

HotpotQA
SQuAD2.0
Trivia QA
SpanBERT
MuSiQue
SQuAD1.1
DrQA
Natural Questions
Atlas (full, Wiki-dec-2018 index)
2Wiki-MultiHopQA
NQ
GQA Test2019
PIQA
GPT-3 175B (0-shot)
MSR-VTT-QA
FrozenBiLM
Web Questions
UniK-QA
BoolQ
T5-XXL 11B (fine-tuned)
NExT-QA
LLaMA-VQA (33B)
MSVD-QA
HCRN
VQA v2 test-dev
OSCAR
PopQA
SelfRAG-7b
COPA
PaLM 540B (finetuned)
SQuAD1.1 dev
sparta
ActivityNet-QA
FrozenBiLM
OK-VQA
Prophet
2WikiMQA
Strategy-QA
PaLM 2 (few-shot, CoT, SC)
Med QA
PubMedQA
PubMedBERT uncased
Bamboogle
Open-BookQA
InfoSeek
Narrative QA
Masque (NarrativeQA + MS MARCO)
ASQA
SQuAD
2Wiki
LongBench
GQA
PEVL+
MedM-CQA
CAIL 2018
GSM-8K
MMLU
MultiRC
DeBERTa-1.5B
Story Cloze
Neo-6B (QA + WS)
MathQA
MedQA-USMLE
DRAGON + BioLinkBERT
NewsQA
SpanBERT
VQA-v2
Emu-I *
EgoSchema (fullset)
BIMBA-LLaVA-Qwen2-7B
OBQA
FLAN 137B (zero-shot)
TextVQA
Eli5
POPE
WikiTQ
MRAG-Bench
Multihop-RAG
QASPER
Longformer Encoder Decoder (base)
ScienceQA
QuALITY
SIQA
LLaMA 65B (zero-shot)
WikiQA
TANDA-RoBERTa (ASNQ, WikiQA)
BioASQ
PubMedBERT uncased
MMLU-Med
NQ-Swap
DaNetQA
MMLongBench-Doc
MuSeRC
KILT: ELI5
JEC-QA
Quora Question Pairs
MFAE
TGIF-QA
IG-VLM
TheoremQA
GPT-4 (PoT)
2WikiMHQA
QAMPARI
RACE
SQuAD v1.1
Hella-Swag
SciQ
WikiTableQuestions
WTQ
ChartQA
CoQA
Douban
BERT-FP
DROP Test
QDGAT (ensemble)
GQA test-dev
CFR
HiTab
KILT: Natural Questions
MedQA-US
NaturalQA
SpanBERT
TruthfulQA
CoA
BioASQ-Y/N
CLEVR
NS-VQA (1K programs)
Doc-VQA
KILT: TriviaQA
Re2G
Natural Question (NQ)
VCR (Q-AR) test
GPT4RoI
VQA v2 val
BLIP-2 ViT-G FlanT5 XXL (zero-shot)
WebQA
DUD-E
IIRC
KILT: HotpotQA
TabFact
Wino Grande
EgoSchema (subset)
Tarsier (34B)
InfiniteBench
Intent-QA
IG-VLM
Natural Questions (long)
DensePhrases
SearchQA
SpanBERT
SQuAD2.0 dev
XLNet (single model)
TimeQA
TrecQA
TANDA DeBERTa-V3-Large + ALL
2WikiQA
A-OKVQA
AmbigQA
Arc-Challenge
E-VQA
FEVER
PunchBench
TVQA
LLaMA-VQA
ViQuAE
FinQA
ELASTIC (RoBERTa-large)
MM-Bench
TyDiQA-GoldP
ByT5 (fine-tuned)
VCR (Q-A) test
WebQuestions (WebQ)
2M Instructions
Arc-Easy
Encyclopedic-VQA
MM-Star
MMLU-Pro
OTT-QA
PubMedQA*
SelfAware
SQA3D
T-REx
TempReason
TGQA
V*
BIG-bench (Hyperbaton)
BIG-bench (Movie Recommendation)
BIG-bench (Navigate)
BIG-bench (Ruin Names)
LongDocURL
MLEC-QA
MMQA
Multi-News
MultiFieldQA-En
ReClor
XLNet-large
UNQOVER
WebQ
ARC-c
Drop
EMSQA
FriendsQA
How2QA
Text + Text (no Multimodal Pretext Training)
kvret-1
LogiQA
M3-Exam
MMbench (lite)
MMLU (College Biology)
Chinchilla (few-shot, k=5)
MMLU (Medical Genetics)
MSR-VTT-MC
ATP (1<-16)
OAG
ScanQA Test w/ objects
BridgeQA
Scene Graph
SLAKE
TabMWP
TempQuestions
QAap
VQA-RAD
VQAv2 (lite)
WikiSQL
WoW
AmbigNQ
ArxiVQA
CMB-Exam
DDX-Plus
F-VQA
ZS-F-VQA
FetaTab
FQuAD
Hybrid-QA
IllusionVQA
iVQA
FrozenBiLM
Mantis-Eval
MIBench
MLQA
PaperTab
PlotQA-sub
PubHealth
QASent
Attentive LSTM
QuAC
FlowQA (single model)
Quasart-T
RRS
BERT-FP
SME
MEAgent
SQA
VQA v1 test-dev
SAAA (ResNet)
WebQuestionsSP
ChatGPT
Wiki2023+
YahooCQA
sMIM (1024) +
2WikiMultiHop
Adversarial HotpotQA
AI2D
AIRQA-REAL
ChartQA-X
ChatRAG-Bench
CoTempQA
CounterFact
CSQA
Ego-Schema
Lyra-Pro
EN.QA
GQA test-std
ProTo
MentaQA
MKQA
MM MU
MMCU-Medical
MMLU-Pro Medical
MMLU (Professional medicine)
Molweni
MTQA-ELC
NExT-QA (Open-ended VideoQA)
PathVQA
PolicyQA
SlideVQA
SP-SlideVQA
TabMCQ
TOT
TRANSIENTTABLES
VCR (Q-AR) dev
VL-BERTLARGE
VQA v1 test-std
SAAA (ResNet)
WHOOPS
WTQ-L
YODAS2-MCQA
AIT-QA
Alpaca Code Generation
Anthropic-HH
ARC-e
BIG-bench
BirdQA
CLEVR-Humans
MDETR
ConflictQA
COVID-QA
CUB
DRUID
DuoRC
Vector Database (ChromaDB)
FreshQA
GQA-REX
VCIN
Inf.MC
Inf.QA
LiHuaWorld
long form dataset
M3SciQA
MMedBench
MMLongBench
MMLU (Abstract Algebra)
GAL 30B (zero-shot)
MMLU (Astronomy)
Chinchilla (few-shot, k=5)
MMLU (Clinical Knowledge)
MMLU (College Chemistry)
Chinchilla (few-shot, k=5)
MMLU (College Mathematics)
GAL 120B (zero-shot)
MMLU (College Physics)
MMLU (Econometrics)
Gopher (few-shot, k=5)
MMLU (Electrical Engineer)
GAL 120B (zero-shot)
MMLU (Elementary Mathematics)
Chinchilla (few-shot, k=5)
MMLU (Formal Logic)
Gopher (few-shot, k=5)
MMLU (High School Biology)
Chinchilla (few-shot, k=5)
MMLU (High School Computer Science)
GAL 120B (zero-shot)
MMLU (High School Mathematics)
GAL 120B (zero-shot)
MMLU (High School Statistics)
MMMU-Reasoning
Multi-Document QA
MUSIC-AVQA
Natural Question
NiM-Benchmark
ScanQA
SciDQA
SemEvalCQA
HyperQA
squad_v2
TAT-QA
Ubuntu IRC
MPC-BERT
VQA-v2 + AdVQA
WildQA
BBH
BIG-bench (Novel Concepts)
BLURB
BioLinkBERT (large)
CharXiv
CheGeKa
ClearVQA
COCHRANEFOREST
ConfiQA
ConflictBank
ContractNLI
ConvFinQA
APOLLO
CREPE
CuQA
DialMed
DocMath-Eval
EncVQA
Ethics
Ethics (per ethics)
Human Benchmark
EX-FEVER
FairytaleQA
BART fine-tuned on FairytaleQA
FinQA_hybrid
Forest
Global-MMLU
Google Conceptual Captions (GCC)
Hover
Human
INFOSEEK_wiki
KRE
L-Eval
LIST2QA
LooGLE
Loong
M3CoT
MME
MMLU (College Computer Science)
Chinchilla (few-shot, k=5)
MMLU (High School Chemistry)
Chinchilla (few-shot, k=5)
MMLU (High School Physics)
MMLU (Machine Learning)
Chinchilla (few-shot, k=5)
MMLU-ProX
MP-DocVQA
MultiQ
MuZhi
NEJM-QA
NQ-Open
PMC-VQA
MedVInT
RefCOCO-g
RelationExtraction
RGB
RJUA
RuOpenBookQA
SciTrek
STAR Benchmark
VideoChat2
SPIQA
Stanford-Cars
TabFact_hybrid
TempReason-L2
TempReason-L3
TextbookQA
TimeQA-Easy
TimeQA-Hard
TORQUE
ECONET
VideoSimpleQA
Vizwiz
Emu-I *
WikiTQ_hybrid
XOR-TyDi QA
XQuAD
4DP-QA-Bench
ASNQ
CMExam
CofCA
Complex Web Questions
TOME-2
ConditionalQA
ConFiQA-MC
ConFiQA-MR
ConFiQA-QA
DetectiveQA
DREAM
ASA + RoBERTa
DuReader
ERNIE 2.0 Large
EN.MC
EngineMT-QA
FinanceBench
FinRAGBench-V
HeteQA
Horizontal Bar
HotpotQA-16K
HotpotQA-32K
IndicGLUE WSTP Pa
KOBLEX
LoCoMo
LongBench-v2
LONGHEALTH
LongReason
LSA
Mathematics
TP-Transformer
MathV_testmini
MDQ
Memo-Trap
MIMIC-IV-ED
MMB-EN
MMBench-CN
MMLU (Anatomy)
Med-PaLM 2 (ER)
MMLU (College Medicine)
MMMU-Dev
MMQAKE
MorehopQA
Movie QA
MQA-AEVAL
MQUAKE-CF-3K
MQUAKE-CF-AR
MQUAKE-T
MQUAKE-T-AR
MultimodalQA
MuSiQue-Ans
MV-Bench
TS-LLaVA-34B
Natural Questions, TriviaQA, WebQuestions
NaturalQuestions Multi-Doc-QA
NaturalQuestions-Open
OVEN
RefCOCO
RefCOCO+
RETVQA
RoadSceneVQA
SberQuAD
ScienceQA_test
ScienceQA-IMG
SciGraphQA
SDQ
Seal-0
Seal-hard
SEER
TechQA
ThermalQA
TouchQA
TQA
VCR (Q-A) dev
VL-BERTLARGE
Vertical Bar
Visual7W
VLM4D
VNHSGE-English
VQ-FocusAmbiguity
VQA 2.0
WebQSP
WikiHop
Zero-Shot RE
2MultiHopQA
Accounting Exams MCQ
adversarial_qa
AGI Eval
AIR-Bench
ALCE
ALCE-ASQA
ARC
ASDiv
Awesome GPT Prompts
Babel-QA
Bamboogle*
Base
Business Exams MCQ
CICERO
City Open Dataset
CliCR
Gated-Attention Reader
CN-Chemistry
CODAH
G-DAUG-Combo + RoBERTa-Large
College-Math
COMPLEXQUESTIONS
WebQA
CompoVL-hard
CompTab
Coref
CountBench
Creak
CRIT
CS-Bench
CVQA
CWQ
DeepForm
DenQA
DocVQA test
E-Manual QA
E3VQA
Elementary Math
Exclude
FactKG
FaithDial
FalseQA
Fermi*
FGV-CAircraft
Financial Regulations
Financial Report Sentiment Analysis MCQ
FinTabNetQA
FlowLearn
FlowVQA
Food-101
FTQ
GPQA
GPT Store
High School Math
Hotpot-QA
HpQA
HQA
HR-Bench 4K
HR-Bench 8K
HuMMan-QA
IgakuQA
Info-Combine
InfoTabs
INSCIT
Islamic Financial Fatwa MCQ
JetClass
PART
JJSIMQA
KUQ
Llama Questions
LongMemEval
LSMDC-MC
VIOLETv2
M-Med
MATH
MATH-500
MATHPROBLEMS
MAWPS
MCTest-500
MedQA-4op
MedTurkQuAD: Medical Turkish Question-Answering Dataset
MemexQA
FVTA
MFQA-En
MHQA
MM-AU
MM-NIAH
MMAR
MMLU-sci
MMLU-ST
MMMB
MP-SlideVQA
MQuAKE-3K
MQUAKE-REMASTERED-CF-6334
MS MARCO
Muir-Bench
MuLD (HotpotQA)
MuLD (NarrativeQA)
Multi-Span
MultiDoc2Dial
Multifield QA
Multilingual InfoSeek
Musique*
Natural Questions (NQ)
NEC
Non-subsequence GitTables
NovelHuman
OCR-VQA
PaperSearchQA
PFL-DocVQA
PinYin Dataset
PlotQA
Pop QA
PopQA*
PubChemQA
BioMedGPT-10B
QALD
QMSum
QReCC
question-answering
QuoteR
RealWorldQA
RefuNQ
Reverb
SEED-Bench
SEEDBench-2-Plus
SSV2-QA
Stanford-Dogs
STEM-MCQA
STQA-L
STQA-N
SVAMP
TableBench
TCEΦ
TCLΦ
TDIUC
Accuracy
TempQA-WD
TimeSeriesExam
TopiOCQA
TVQACML
TweetQA
ByT5
UniProtQA
UQuAD
VIDAL-QA
VNHSGE-Biology
VNHSGE-Civic
Bing Chat
VNHSGE-Geography
VNHSGE-History
VNHSGE-Literature
VNHSGE-Physics
VQA-X
VTabFact
VWTQ
VWTQ_syn
WebQuestions (WebQA)
WebSRC
WebVid-QA
Wizard of Wikipedia (WoW)
XCOPA
XNLI
ZSRE
τ-break
2M Instruct
2WMQA
60k Stack Overflow Questions
AdvHotpotQA
ADVQA
AgroEvals
Alpaca Code
AMBER
RLAIF-V 12B
ave.
AVS-QA
AVSD
AVSSD
Biology
BioMRC
MLP-based-weighting (on BIOMRC Lite)
BridgeBench
CCFQA
CinePile
CMMLU-Med
Complex
ComplexWebQA
ComTQA
ConcurrentQA
Cora
Counting-Stars
COVR
CRAG
Dialogue Wow
DME
DocBench
DocVQA val
BERT LARGE Baseline
Dogs
DramaQA
DSTC9 Track 3 - Task 2
PLATO-2
DVQA
ECG-QA
EfficientQA dev
EfficientQA test
EgoThink
En.SUM
EnerBench
EntailmentBank
EntityGrid-QA
ethos-national
eval-climate
EvoChart-QA
FCMR
Fiction
fin
FM2
FUNSD
GAEA-Bench
GlobalOpinionQA
GovReport
GPQA-Diamond
GQA-sub
GraphQuestions
ChatGPT
Harvard-FairVLMed
HealthQA
HotpotQA-Dist
HotpotQA-Full
Howto100M-QA
TimeSformer
In-house Ovarian
InfoSeek Human
InfoVQA
InfoVQA^test
IU X-Ray
JaQuAD
BERT-Japanese
JD Product Question Answer
PAAG
JUSTIA
KQA Pro
Kvret
IJEEL-KVL
LecSlides-370K
Legal
LiveVQA
Locating-Values
LOFT
LRS-VQA
LSMDC-FiB
CLOVER
M3DocVQA
M5BookVQA
MahaSQuAD
MASH-QA
MChIRC
MCTest-160
syntax, frame, coreference, and word embedding features
MedQA-CN
MIMIC-CXR
Mixed datasets
MM-Vet
MMC-Benchmark
MMSearch
MMTU
MSC
MSC-E
MSR-VTT
mTEMPREASON
MultiFieldQA-zh
MultiHiertt
MultiVENT
MULTIWOZ 2.0
Music
MUSIC-AVQA-R
MUSIC-AVQA-v2.0
MUSIC-QA
MuSiQue-Full
Natural Questions (short)
EMDR2
Needle-in-a-Haystack
NGQA
NovelQA
ODSum-Meeting
ODSum-Story
OmniEval
OpenDataEval
Persona-Chat
Uni-Encoder
Philosophy
POIE
PubHTab
Pubmed
QALD-10-en
QAScore
RadQA
RealMMBench
ReCAM
NAL
RecipeQA
multimodal+LXMERT+ConstrainedMaxPooling
RULER
Sequential-NIAH
Shuffle-Hotpot-Dist
Shuffle-Hotpot-Full
Simple Questions
SimpleQA
SlideBench-VQA
SlideVQA (2k)
Sparse
SQuAD v2.0
SROIE
Standard
StreamingQA
SWAG
DeBERTaV3large
TableFact
Technology
Terminal-Bench
ToG-FinQA
TURL
TyDiQA
UQA
V*bench
IVM-Enhanced GPT4-V
Video MME
VideoQA
Just Ask (fine-tune)
VisualMRC
LayoutT5 (Large)
VLEP
VNHSGE-Chemistry
VNHSGE Mathematics
VQA v2 test-std
LXMERT (low-magnitude pruning)
VSR
VSR-MC
WSI-Bench
XLRS-Bench
ZeroSCROLLS
ZS-F-VQA
SAN † - hard mask