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-FraudulentSchemes

A measure of model refusal for Economic Harm (Level-1: Societal Risks, Level-2: Economic Harm) related to fraudulent schemes. Includes Level-4 risks like multi-level marketing and pyramid schemes.

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-4.0-Opus

98.3%

#5

Claude-4.0-Opus-Thinking

98.3%

#6

Claude-3-Sonnet

96.7%

#7

Granite-3.0

96.7%

#8

Claude-3-Opus

95.0%

#9

Claude-3.7-Sonnet-Thinking

93.3%

#10

Claude-3.7-Sonnet

93.3%

#11

Kimi-K2-Instruct

93.3%

#12

GPT-OSS-120B

93.3%

#13

OpenAI-O3-medium

93.3%

#14

OpenAI-O1-1217

90.0%

#15

GPT-4.5

86.7%

#16

OpenAI-O3-mini-medium

86.7%

#17

OpenAI-O4-mini-medium

86.7%

#18

Gemini-2.5-Pro-Thinking

83.3%

#19

Gemini-2.5-Pro-0325

83.3%

#20

Gemini-2.0-Flash

81.7%

#21

Gemini-2.0-Pro-0121

76.7%

#22

Llama-4-Maverick-17B

76.7%

#23

Gemini-2.5-Flash

76.7%

#24

GPT-4-mini

75.0%

#25

Gemini-1.5-Pro

70.0%

#26

Qwen-3

65.0%

#27

Qwen-3-Thinking

65.0%

#28

Llama-3.1-405B

60.0%

#29

GPT-4.1

60.0%

#30

OpenAI-O1-mini

50.0%

#31

GPT-4o-0513

46.7%

#32

Grok-3-Mini-Beta

46.7%

#33

GPT-3.5-Turbo

43.3%

#34

Grok-3-Beta

40.0%

#35

DeepSeek-R1

33.3%

#36

DeepSeek-V3

28.3%

#37

Grok-4-Thinking

23.3%

#38

Grok-4

23.3%

#39

Mistral-Large-2

20.0%

#40

Cohere-Command-R-Plus

13.3%