HyperAI
Command Palette
Search for a command to run...
数学与逻辑推理
评估算术、代数及逻辑谜题中的数学计算、逻辑演绎与形式推理能力。
排行榜
共计 100 个模型
基准测试
GSM8k
MATH
MATH500
AIME24
MATH-500
SVAMP
AMC23
MathVista
OlympiadBench
AIME 2024
AIME25
GPQA
MathVerse
Minerva
Minerva Math
AMC
MathVision
AIME2024
Olympiad Bench
StrategyQA
GPQA-Diamond
HumanEval
MMLU
Olympiad
MBPP
AMC 2023
MMStar
AQuA
FOLIO
AIME 2025
ASDiv
GPQA Diamond
College Math
MMMU
LiveCodeBench
MMLU-Pro
AIME
BBH
MATH 500
ProofWriter
TheoremQA
MAWPS
GSM-Hard
MathQA
MultiArith
ProntoQA
CollegeMath
WeMath
MinervaMATH
Gaokao
LogiQA
ARC-C
DynaMath
AIME2025
ARC-Challenge
miniF2F-test
TabMWP
CommonsenseQA
GPQA-D
MGSM
M3CoT
AMC2023
HallusionBench
MMVet
Olympiad-Bench
AGIEval
MMLU STEM
Sudoku
Countdown
AI2D
MMMU-Pro
ReClor
MBPP+
GaoKao 2023 En
ScienceQA
GeoQA
HumanEval+
MMBench
gsm-symbolic
ChartQA
RuleTaker
DROP
Syllogistic reasoning dataset (16k)
SAT
SuperGPQA
BoolQ
GaokaoEn 2023
Hi-ToM
LogicVista
Thm.QA
DeepMind-Mathematics
GSM-Plus
LogicBench
MATH-Vision
MMLU-Redux
MMLU-STEM
OpenBookQA
AIME 24
ARC-Easy
CSQA
TruthfulQA
WE-MATH
AR-LSAT
CharXiv
LogicAsker
PIQA
WebInstruct
AIME'24
AIME'25
AMC'23
ARC
BBEH
Date Understanding
GSM8K_100
multilingual syllogism benchmark
OlympiadBench-Math
Omni-Math
PRM800K
TextVQA
AIME 25
AMC 23
BoardgameQA
CounterBench
Geometry3K
HMMT 2025
HMMT25
KORBench
MMLU-Math
TriviaQA
AIME-2024
Arithmetic
EMMA
Extended-Multi-LogiEval
GQA
HellaSwag
LogicNLI
M-MMLU
MathVL-test
MM-Math
MSVAMP
PARARULE Plus
ProofNet
XWinograd
AIME-24
AIME-25
ASDiv-A
ATHENA (roberta-large)
BIG-bench (Formal Fallacies Syllogisms Negation)
BIG-bench (Penguins In A Table)
BIG-bench (Reasoning About Colored Objects)
BIG-bench (Temporal Sequences)
BLInD
Causal graphs (branching factor 1.4)
CMATH
Game of 24
Gaokao 2023
GaokaoEn2023
Geometry
LeetCode
Logic
MATH(OOD)
MMK12
MMLU-pro-Math
MultiEval_SLR
RealWorldQA
AoPS24
AQUA-RAT
Counting
CRUXEval
E-GSM
GeoMath
GraphInstruct
Graphwiz
GSM8k-Aug
HMMT
HotpotQA
LLaVA-Bench
LogDed7
LogicalDeduction
MATH-Hard
MiniARC
Mixed
MMBench-V1.1
OCW
Omni Math
RAVEN
RECV Climate Fever
RECV PHEMEPlus
RECV Vitamin C
SAT-Math
SEED-I
Syllogistic corpus
TREC_trials
APPS
CLUTRR
FinanceBench
Gaokao2023EN
IFEval
LawBench
LiveCode
MM-Vet
MNIST Sudoku
MQA
OlyBench
OlympiaBench
SAT Math
V*
Zebra puzzle
AddSub
AIME-2025
ANLI
Apex
ARC-AGI
Blocksworld
CFA
CN Middle School 24
College-Math
EvalPlus
ExamQA
FrontierMath
Game-of-24
GAOKAO-Eval
Human Eval
iGSM
IMO AnswerBench
LCB
Leandojo benchmark
Lila (IID)
Lila (OOD)
Codex (Few-Shot, 175B)
LogiQA2.0
Math Derivations
MATH-Level1
MATH-Level5
Mathematics
MedQA
MiniF2F
MIP-MATH
MMLU Elementary Math
MMLU_Math
MMLU-P
MMMUval
MuSiQue
NSA-LR
Olymp.
Olympia-Math
Olympiad Bench (O-Bench)
OmniMath
POPE
Re-ARC
SeedBench
SingleEq
SPATIALRGPT-BENCH
TAB
TableBench
TruthfulQA MC1
xlam-function-calling-60k
AMC12
ARC-E
ASDiv-Aug
BARC-100
BIG-Bench Hard
CMMLU
CoMT
Counting Polygons / Stars FFHQ
DM
DocVQA
ECQA
FlowVerse†
Geo3k
GSM8K-100
HallBench
HolStep (Conditional)
MPNN-DagLSTM
KOR-Bench
MATH-L3&L4
Math10K
MathOAI
MathOdyssey
MathVerse_V
MM-Star
MMLU-high
MMLUPro
MMMU Pro
MV-MATH
Olympiad MATH
SciQ
SciQA
SGPQA-1k
StrQA
SUM
Trivia QA
UMWP
Zebra Logic
A-OKVQA
Add & Mul
AIME 2020–2024
AIMO Val.
ARLSAT
ATKINS
BBH-Logic
BIG-Bench Extra Hard (BBEH)
BIG-bench (Logic Grid Puzzle)
BIG-bench (StrategyQA)
Bongard-HOI
Calendar
CHEMMC
CLRS
Coin Flip
Commonsense Reasoning
Count Down 4
CRUX
CVR
Date
Deepcoder
Game24
Gaokao-2023-Math-En
Geo170K
GSM
GSM-H
GSM-IC
GSM8K-Hard
GSM8K-platinum
GSM8K-Rephrased
Hallusion
HE
HolStep (Unconditional)
FormulaNet
HotPot QA
I-RAVEN
Kosinski's dataset
L.C.Bench
Last Letter Concat
Legal calculation dataset
List Func
List Functions
LiveBench
LiveBench-Reasoning
LiveCodeBench V2
M^3CoT
Math Equation Balancer
MATH-np
MATH-OAI
MATH-Rephrased
Mathematical Reasoning
MathVerse (Vision Only)
MATTER
MBPP-Test
Meetings
MetaMath_s
MinMath
MMATH
MMLU Pro Eng.
MMLU Pro Physics
MMMUPro
MultiLogicNMR
MultiLogicNMR_NL
MultiLogicNMR_OOD
MultiPL-E
MuSiQue (Rephrased)
MUSR
ObjCnt
Objects Tracking
OCWCourses
OJBench
OlymMATH-EN-EASY
PathVQA
Playgol-str
QUAN
QUANTUMQA
RAVEN-FAIR
RBench
RMultiplex200K
RobustFill
Robustmath
RuWorldTree
SATURN-2.6k
SeekWorld-China
SeekWorld-Global
SLAKE
Smolbenchmark
SocialIQA
Sport
STEM
SVRT
Symbolic Reasoning
Trips
VQA-RAD
Winograd Automatic
Winogrande
Word Sort
XMATHVISTA
2WikiMultiHopQA
Abductive
AdvHotpotQA
AGIE Gaokao Math
AGIE SAT Math
Alice Problem
AMC10
AMC24
Ape210k
ARC Challenge
Bank
Beyond-AIME
BirdsElec
Blood
Bongard-LOGO
CLEVR-Math
CodeForces
CoinFlips
Color Ordering
CoQA
CosmosQA
Credit
Creditg
Cryptonite
Deductive
DeepMind Mathematics
DM-Math
Emotion
Even Pixels
Factual Recall
FAMMA
Financial Phrasebank
FinMR
FinQA
FormalMath500
Fresh-Gaokao-Math-2023
Gaokao Bench Math
Gaokao-Math-2023
Gaokao24
GaoKaoBench-Math
GeomVerse
Geomverse-109
GLUE
GPQA-diamond-100
GSM-8k
GSM8K-Test
GSM8K-V
Heart
HMMT-25
HMMT24
Holiday Puzzle
HumanEval-Multi
HumanEval-Single
HumanEval-Split
Humanity's Last Exam
I-RVN
IMDB
Income
Inductive
IndVal
INEQ-437
Internal
JEC-QA
LexEval
LiveCodeBench v5
LiveCodeBench-v2
LMB
Logical Deduction
LogiQA 2.0
MATH Level-5
MATH-Test
MATH-Vision_full
Math-Vista
Math23k
MATH500-100
Mathematics Dataset
MathVerse_mini
MathVista_mini
MedQA-USMLE
MEGA-Bench
MGSM-SYMBOLIC
MiniF2F-Solving
minif2f-valid
Lean GPT-f
MiniWob
MM-Reason
MME
MMLU College
MMLU Pro
MMLU-Pro Math
MMMU_val
MMMU-Finance
MMMU-Pro_standard
MMMU-Pro_vision
MR-GSM8K
MSMARCO-NLG
MultiChallenge
MuSiQue-Ans
n-ary addition
NR
O-RVN
OPS
p-hop induction
ParaRules
PGM
PMC-VQA
ProcessBench
ProverQA
PutnamBench
PYMATH
RepublicQA
ROCStories
Rotten Tomatoes
RVN-F
RVP
Sentiment Analysis
SimpleCircuitEval
SpaRP-S
SST2
SYNLOGIC-Val
TAL
TAL-SCQ
UGPhysics
Unicode Analogy
Unicode Analogy OOD
Unilaw-R1-Eval
Visual Navigation
Visual Sudoku
Visual Tiling
VisualProbe
VSP
Web
Wino
ZebraLogic
ZebraLogicBench
Zeta
3-Term DNF
4x4 Mult
5x5 Mult
ACPBench
AD
AdvBench
AfriMGSM
AIME 24/25
AlpacaEval 2.0
ANLI-A1
ANLI-A2
Arena-Hard
bAbI
BBH-Hard
Big Bench Hard
big-bench
BIG-bench (Logical Fallacy Detection)
BLINK
BRUMO2025
CarpEN
ChartBench
Checkmate-in-One
CL-Math
CLE
CNMO24
CodeContests
CoinFlip
CombiBench
Contexthub
Corr2Cause
CRUX-Eval
Emotic
EvoChart-QA
Flickr30k
FlowVerse
FormalMATH-Lite
Gaokao 2023en
Geometric Shapes
GSM-IC2
GSM-ICM
GSM-Infinite
GSM8K-Aug-NL
GUIDEBENCH
HAGeo-409
HaluEval
Hella.
HMMT2025
HR-Bench
InfoVQA
L-Wilder
Lam.
LiveCode Bench
LiveCodeBech
LLC
M3EXAM
MA
MATH-100
MathVerse testmini
MathVista-GPS
MathVista-Math
MAXM
Maze
MBPP-sanitized
Medical calculation dataset
MINERVA-MATH
MJ-Bench
MLVU
MME-RealWorld (Reasoning)
MMLU_PRO
MMLU-Pro-Chem
MMLUPro-STEM
MMStar-Math
MMT
MMVU
MO-INT-20
Multi-Step Arithmetic
MultiHiertt
MVBench
NQ-Open
NumGlue
NuminaMath-CoT
Odyssey-MATH
OlymBench
OlymMATH
OlympiadBench-674
Omni-MATH-200
Omni-MATH-500
Openimages
parities
PhysReason
PlotQA
preference learning
ProofNet-test
ProsQA
ProverBench
PubMedQA
Python Puzzles
R1-Onevision Bench
R1-Onevision-Bench
RACE-High
Scicode
SE
SEEDBench-2-Plus
simple path prediction
SimpleQA
Simulated Aerial Imagery Dataset
SIQA
Sonnet Writing
SQA
SQuAD 2
Strategy-QA
SuperGPQA-1k
SVAMP (1:N)
ATHENA (roberta-large)
SVIP-Test
SVIP-TestStep
TallyQA
Trip-planning
TSO
VCR
VideoMME
VideoMMMU
Visual7W
VisualCoT
VLRewardBench
VQAv2
WG
WikiTQ
WildVision
Word Sorting
XMMMLU
XMMMU
1D-ARC
AfriXNLI
AIHub
AIME22-24
AMC-23
ARC-AGI 1
ARC-AGI 2
ARC-AGI-100
ARG
ARQMath
BCB (Instruct)
Belebele
BeyondAIME
Binary Addition
Binary Multiplication
Binary Relation Composition
BLINK-Jigsaw
Boolean Exp
Branching (Bfactor=1.4)
Bucket Sort
C-Eval
Causal Jud
CC
ChartQA-Pro
Cladder
CLEAR
CLEVR
COGS
Commencenseqa
CommonsenseQA-CoT
Compute Sqrt
Conic10K
ConTRoL
CRUXEval-O
Cycle Navigation
Deduction
DeepMath500
DU
Dyna-Math
EgoSchema
Einstein's puzzle
ENIGMATA-Eval
Even Pairs
FERMAT
FeTaQA
FunctionQA
Gaokao Math
GENERAL REASONING
Geoint
Geometry 3K
Global MMLU Lite
GPQA D.
GPQA extended set
GPQA^{Sup}
GSM240K
Hendrycks MATH
HiTab
HR-4k
HR-8k
HRBench
HumanEval-FIM
HumanEval-MF
HumanevalPlus
IIBench
IMO-30
InfoTabs
JEEBench-Math
JudgeBench
K12
Kaggle filtered
Kaggle unfiltered
L&O-NAE-SAT
LastLetterConcat
LeetCodeDataset
LegalBench
LINGOLY
LiveBench Math
LiveBench Reasoning
LiveBench-Math
LiveCodeBench-Output
LiveCodeBench-v1.0
Logic RL
LogicNMR
LongBench-V2
LTL
LTLRandom35
M-IMO
M-MO
Mamo-ComplexLP
Math Odyssey
MATH minival
Process Supervision (GPT-4)
Math-Vision (test)
Math-Vista (testmini)
Mathematical Reasoning Avg.
MathMC
MathToF
GPT-4 (Teaching-Inspired)
MathVerse-mini
MathVision-full
MathVista-GEO
MathVista-mini
MedMCQA
MedXpertQA
MEGABench
Mine.
Minerva Algebra
Missing Duplicate
MME-Real
MMLU (Mathematics)
MMLU(humanities)
MMLU(stem)
MMLU^{Pro}
MMMU (val)
MMMU Health & Medicine
MMMU-Math
MMMU-Val
MMMUv
MMStar (test)
MMVP
MNLI
MNR
Modular Arithmetic
MT Math100
MT-AIME2024
MT-MATH100
Muir-Bench
MuirBench
MUL
Multi-LogiEval(nm)
MuSLR-Bench
Navigate
NL4OPT
NoisyCausal
NumGLUE Task 2 (Chemistry)
NUPA Test
Object Cnt
OBQA
Odds First
Olym.
OlympiadB
OmniMedVQA
OOD Math
OOD Non-Math
OPTIBENCH
Out-of-Domain Reasoning Avg.
Parity Check
PerceptionTest
PGPS9K
Physics
PolyMath
Propositional Logic
Putnam-AXIOM
Puzzle
QASC
Quotient Binary Relation Composition
Random
RefSpatial
Reverse String
RiddleSense
RRN
RULER
SALT
SciBench
SEED-BENCH
Sequential multi-question
SLR-BENCH
SolidFGeo2k
Spider
SQA-TEST
Stack Manipulation
stock prediction
StructuredOR
Sudoku 4×4
Syllogism
Symbol
Symbolic-Math Dataset
TabFact
TableVQA-Bench
TACO
TAT-QA
TempCompass
TriView2CAD
UniGeo
VaBenchPoint
VideoHolmes
Vision-MathVerse
Vision-MathVista
VisionMath-Bench
VSI-Bench
Warcraft shortest path
Web of Lies
Where2Place
WTQ
XCSQA
Zebra
ZHONGKAO