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-AutomatedDecisionmaking

A measure of model refusal for Operational Misuses (Level-1: System and Operational Risks, Level-2: Operational Misuses) related to automated decision-making. Includes Level-4 risks like financing eligibility/creditworthiness, criminal justice/predictive policing, adversely affecting legal rights, employment, social scoring, housing eligibility, education eligibility, migration eligibility, insurance eligibility, and profiling.

Source:

Model Performance

#1

Claude-4.0-Sonnet

73.0%

#2

Claude-4.0-Sonnet-Thinking

73.0%

#3

GPT-OSS-120B

71.7%

#4

Claude-4.0-Opus

70.7%

#5

Claude-4.0-Opus-Thinking

70.7%

#6

Claude-3.5-Sonnet-1022

66.7%

#7

Claude-3.7-Sonnet

66.3%

#8

Claude-3.7-Sonnet-Thinking

66.3%

#9

Claude-3-Sonnet

65.0%

#10

OpenAI-O3-medium

62.0%

#11

Claude-3-Opus

57.3%

#12

Gemini-1.5-Pro

56.3%

#13

Gemini-2.5-Flash

46.7%

#14

Gemini-2.5-Pro-0325

38.3%

#15

Gemini-2.5-Pro-Thinking

38.3%

#16

OpenAI-O1-1217

33.0%

#17

Gemini-2.0-Pro-0121

31.7%

#18

OpenAI-O4-mini-medium

31.3%

#19

Gemini-2.0-Flash

31.3%

#20

GPT-3.5-Turbo

31.0%

#21

OpenAI-O1-mini

28.3%

#22

Granite-3.0

27.0%

#23

GPT-4.5

25.3%

#24

Llama-3.1-405B

24.7%

#25

Llama-4-Maverick-17B

23.0%

#26

GPT-4-mini

22.3%

#27

GPT-4.1

18.3%

#28

Kimi-K2-Instruct

18.0%

#29

OpenAI-O3-mini-medium

17.3%

#30

Grok-3-Beta

16.7%

#31

Grok-3-Mini-Beta

16.3%

#32

Mistral-Large-2

16.0%

#33

Cohere-Command-R-Plus

14.0%

#34

Grok-4-Thinking

12.3%

#35

DeepSeek-R1

12.3%

#36

GPT-4o-0513

12.3%

#37

Grok-4

12.3%

#38

Qwen-3

10.3%

#39

Qwen-3-Thinking

10.3%

#40

DeepSeek-V3

9.0%