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

AIR-Bench-Misrepresentation

A measure of model refusal for Manipulation (Level-1: Societal Risks, Level-2: Manipulation) related to misrepresentation. Includes Level-4 risks like automated social media posts, not labeling content as AI-generated, and impersonating humans.

Source:

Model Performance

#1

Claude-3.5-Sonnet-1022

94.4%

#2

OpenAI-O1-1217

91.1%

#3

OpenAI-O3-medium

91.1%

#4

GPT-OSS-120B

91.1%

#5

Claude-4.0-Sonnet-Thinking

90.0%

#6

Claude-4.0-Sonnet

90.0%

#7

OpenAI-O4-mini-medium

87.8%

#8

Granite-3.0

86.7%

#9

Claude-4.0-Opus-Thinking

85.6%

#10

Claude-4.0-Opus

85.6%

#11

Kimi-K2-Instruct

83.3%

#12

Claude-3-Opus

83.3%

#13

Claude-3.7-Sonnet

82.2%

#14

Claude-3.7-Sonnet-Thinking

82.2%

#15

Claude-3-Sonnet

80.0%

#16

OpenAI-O3-mini-medium

67.8%

#17

Gemini-2.5-Pro-Thinking

61.1%

#18

Gemini-2.5-Pro-0325

61.1%

#19

GPT-4.5

60.0%

#20

Gemini-2.0-Pro-0121

58.9%

#21

Gemini-2.5-Flash

52.2%

#22

Llama-4-Maverick-17B

52.2%

#23

Gemini-2.0-Flash

48.9%

#24

DeepSeek-R1

47.8%

#25

GPT-4.1

45.6%

#26

Grok-3-Mini-Beta

45.6%

#27

Grok-3-Beta

44.4%

#28

Gemini-1.5-Pro

43.3%

#29

Llama-3.1-405B

41.1%

#30

GPT-4-mini

38.9%

#31

GPT-3.5-Turbo

38.9%

#32

Qwen-3

37.8%

#33

Qwen-3-Thinking

37.8%

#34

GPT-4o-0513

33.3%

#35

Grok-4-Thinking

30.0%

#36

Grok-4

30.0%

#37

OpenAI-O1-mini

27.8%

#38

DeepSeek-V3

22.2%

#39

Mistral-Large-2

14.4%

#40

Cohere-Command-R-Plus

10.0%