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-DisempoweringWorkers

A measure of model refusal for Economic Harm (Level-1: Societal Risks, Level-2: Economic Harm) related to disempowering workers. Includes Level-4 risks like undermining workers' rights, worsening job quality, encouraging undue worker surveillance, and causing harmful labor-force disruptions.

Source:

Model Performance

#1

Claude-3.5-Sonnet-1022

100.0%

#2

Claude-4.0-Sonnet

100.0%

#3

Claude-4.0-Sonnet-Thinking

100.0%

#4

Claude-3-Sonnet

98.3%

#5

Claude-4.0-Opus-Thinking

96.7%

#6

Claude-4.0-Opus

96.7%

#7

GPT-OSS-120B

96.7%

#8

Claude-3.7-Sonnet

95.0%

#9

Claude-3.7-Sonnet-Thinking

95.0%

#10

Claude-3-Opus

93.3%

#11

Granite-3.0

90.8%

#12

OpenAI-O3-medium

90.0%

#13

Kimi-K2-Instruct

88.3%

#14

Gemini-2.5-Pro-Thinking

87.5%

#15

Gemini-2.5-Pro-0325

87.5%

#16

OpenAI-O4-mini-medium

86.7%

#17

GPT-4.5

85.0%

#18

OpenAI-O1-1217

80.8%

#19

Gemini-2.0-Pro-0121

77.5%

#20

OpenAI-O3-mini-medium

75.8%

#21

Gemini-2.0-Flash

75.0%

#22

Gemini-2.5-Flash

74.2%

#23

Gemini-1.5-Pro

73.3%

#24

Llama-4-Maverick-17B

70.8%

#25

GPT-4.1

63.3%

#26

Llama-3.1-405B

60.0%

#27

Qwen-3

51.7%

#28

Qwen-3-Thinking

51.7%

#29

Grok-3-Mini-Beta

51.7%

#30

GPT-4-mini

43.3%

#31

DeepSeek-R1

37.5%

#32

GPT-4o-0513

36.7%

#33

GPT-3.5-Turbo

33.3%

#34

OpenAI-O1-mini

33.3%

#35

Grok-4-Thinking

27.5%

#36

Grok-4

27.5%

#37

Grok-3-Beta

27.5%

#38

DeepSeek-V3

24.2%

#39

Mistral-Large-2

20.0%

#40

Cohere-Command-R-Plus

13.3%