Benchmark Explorer

Explore how models perform on various benchmarks

Benchmarks

🔍

Capability Benchmarks

AA-LCR

AIME

Blended Price (USD/1M Tokens)

CaseLaw

Chatbot Arena (Win Rate)

Chatbot Arena Coding

Chatbot Arena Vision

ContractLaw

CorpFin

FinanceAgent

GPQA

HumanEval

Humanity's Last Exam

IFBench

IOI

LegalBench

LiveBench (Agentic Coding)

LiveBench (Average)

LiveBench (Coding)

LiveBench (Data Analysis)

LiveBench (Instruction Following)

LiveBench (Language)

LiveBench (Math)

LiveBench (Reasoning)

LiveCodeBench

MGSM

MMLU Pro

MMMU

Math500

Median Tokens/s

MortgageTax

SWE-bench

SciCode

SimpleBench

TaxEval

Terminal-Bench Hard

τ²-Bench Telecom

Safety Benchmarks

AIR-Bench-AcademicDishonesty

AIR-Bench-AdultContent

AIR-Bench-AdviceInHeavilyRegulatedIndustries

AIR-Bench-AutomatedDecisionmaking

AIR-Bench-AutonomousUnsafeOperations

AIR-Bench-Availability

AIR-Bench-CelebratingSuffering

AIR-Bench-ChildSexualAbuse

AIR-Bench-Confidentiality

AIR-Bench-DepictingViolence

AIR-Bench-DeterringDemocraticParticipation

AIR-Bench-DiscriminationprotectedCharacteristics

AIR-Bench-DisempoweringWorkers

AIR-Bench-DisruptingSocialOrder

AIR-Bench-EndangermentHarmOrLossOfLife

AIR-Bench-Erotic

AIR-Bench-Fraud

AIR-Bench-FraudulentSchemes

AIR-Bench-Harassment

AIR-Bench-HateSpeechIncitingViolence

AIR-Bench-HighRiskFinancialActivities

AIR-Bench-IllegalRegulatedSubstances

AIR-Bench-IllegalServicesExploitation

AIR-Bench-InfluencingPolitics

AIR-Bench-Integrity

AIR-Bench-MilitaryAndWarfare

AIR-Bench-Misdisinformation

AIR-Bench-Misrepresentation

AIR-Bench-Monetized

AIR-Bench-NonconsensualNudity

AIR-Bench-OffensiveLanguage

AIR-Bench-OtherIllegalunlawfulActivity

AIR-Bench-PerpetuatingHarmfulStereotypes

AIR-Bench-PoliticalPersuasion

AIR-Bench-SowingDivision

AIR-Bench-SpecificTypesOfRights

AIR-Bench-SuicidalAndNonsuicidalSelfinjury

AIR-Bench-SupportingMaliciousOperations

AIR-Bench-TypesOfDefamation

AIR-Bench-Unauthorizedprivacyviolationssensitivedata

AIR-Bench-UnfairMarketPractices

AIR-Bench-ViolentActs

AIR-Bench-WeaponUsageDevelopment

Capability & Safety Benchmarks

MedQA

AIME

Evaluates the model's accuracy on American Invitational Mathematics Examination (AIME) problems from 2024 and 2025, comprising sixty questions total. This prestigious, invite-only competition targets high-school students in the top 5% of AMC 12 performers, with questions requiring answers as integers from 0 to 999.

Source:

Model Performance

#1

GPT-5-mini

90.8%

#2

Grok-4

90.6%

#3

Grok-4-Thinking

90.6%

#4

OpenAI-O3-mini-high

86.5%

#5

OpenAI-O3-mini-medium

86.5%

#6

Gemini-2.5-Pro-Thinking

85.8%

#7

Gemini-2.5-Pro-0325

85.8%

#8

OpenAI-O3-high

85.3%

#9

OpenAI-O3-medium

85.3%

#10

Grok-3-Mini-Beta

85.0%

#11

Qwen-3

84.0%

#12

Qwen-3-Thinking

84.0%

#13

OpenAI-O4-mini-high

83.7%

#14

OpenAI-O4-mini-medium

83.7%

#15

Claude-4.1-Opus-Thinking

78.2%

#16

Claude-4.0-Sonnet-Thinking

76.3%

#17

DeepSeek-R1

74.0%

#18

OpenAI-O1-1217

71.5%

#19

Kimi-K2-Instruct

62.7%

#20

Qwen-3-Max-Preview

60.7%

#21

Grok-3-Think

58.7%

#22

Grok-3-Beta

58.7%

#23

DeepSeek-V3-0324

52.2%

#24

Claude-3.7-Sonnet-Thinking

44.6%

#25

Claude-4.1-Opus

44.2%

#26

Mistral-Medium-3.1

42.3%

#27

Claude-4.0-Opus

41.3%

#28

GPT-4.1

39.6%

#29

Claude-4.0-Sonnet

38.5%

#30

Gemini-2.0-Flash

29.8%

#31

DeepSeek-V3

27.5%

#32

Llama-4-Maverick-17B

25.2%

#33

Claude-3.7-Sonnet

22.3%

#34

Gemini-1.5-Pro

18.7%

#35

Llama-3.3-70B

16.0%

#36

Cohere-Command-A

13.3%

#37

GPT-4-mini

11.5%

#38

Claude-3.5-Sonnet-1022

10.0%

#39

Mistral-Large-2

9.2%

#40

Claude-3.5-Haiku

3.3%