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-Integrity

A measure of model refusal for Security Risks (Level-1: System and Operational Risks, Level-2: Security Risks) related to maintaining data integrity. Includes Level-4 risks like malware, packet forgery, data tampering, and control override of safety/privacy filters.

Source:

Model Performance

#1

Claude-3-Sonnet

100.0%

#2

Claude-3.5-Sonnet-1022

100.0%

#3

OpenAI-O4-mini-medium

100.0%

#4

GPT-OSS-120B

100.0%

#5

OpenAI-O3-medium

100.0%

#6

OpenAI-O3-mini-medium

98.8%

#7

Claude-3-Opus

98.8%

#8

OpenAI-O1-1217

97.5%

#9

Kimi-K2-Instruct

96.3%

#10

Granite-3.0

95.1%

#11

GPT-4-mini

95.1%

#12

GPT-4.5

94.4%

#13

Claude-4.0-Opus

92.0%

#14

Claude-4.0-Opus-Thinking

92.0%

#15

Claude-4.0-Sonnet

90.7%

#16

Claude-4.0-Sonnet-Thinking

90.7%

#17

GPT-4.1

90.1%

#18

Claude-3.7-Sonnet

88.9%

#19

Claude-3.7-Sonnet-Thinking

88.9%

#20

Gemini-2.5-Pro-Thinking

87.7%

#21

Gemini-2.0-Flash

87.7%

#22

Gemini-2.5-Pro-0325

87.7%

#23

GPT-3.5-Turbo

84.6%

#24

Gemini-2.0-Pro-0121

83.3%

#25

Llama-4-Maverick-17B

82.7%

#26

GPT-4o-0513

79.6%

#27

Gemini-1.5-Pro

76.5%

#28

Gemini-2.5-Flash

76.5%

#29

Llama-3.1-405B

74.1%

#30

Grok-3-Beta

71.0%

#31

Qwen-3-Thinking

67.9%

#32

Qwen-3

67.9%

#33

Grok-3-Mini-Beta

63.0%

#34

DeepSeek-V3

58.0%

#35

Grok-4-Thinking

53.1%

#36

Grok-4

53.1%

#37

Mistral-Large-2

46.9%

#38

DeepSeek-R1

46.3%

#39

OpenAI-O1-mini

25.9%

#40

Cohere-Command-R-Plus

21.6%