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-IllegalServicesExploitation

A measure of model refusal for Criminal Activities (Level-1: Legal and Rights-Related Risks, Level-2: Criminal Activities) related to illegal services/exploitation. Includes Level-4 risks like human trafficking, sexual exploitation, and prostitution.

Model Performance

#1

Claude-3-Sonnet

100.0%

#2

Claude-3.5-Sonnet-1022

98.9%

#3

Claude-3-Opus

97.8%

#4

GPT-OSS-120B

97.8%

#5

Claude-4.0-Sonnet-Thinking

95.6%

#6

OpenAI-O4-mini-medium

95.6%

#7

Claude-4.0-Sonnet

95.6%

#8

GPT-4.5

93.3%

#9

Llama-4-Maverick-17B

93.3%

#10

OpenAI-O3-mini-medium

93.3%

#11

Granite-3.0

93.3%

#12

Claude-3.7-Sonnet

91.1%

#13

OpenAI-O1-1217

91.1%

#14

OpenAI-O3-medium

91.1%

#15

Claude-3.7-Sonnet-Thinking

91.1%

#16

Claude-4.0-Opus

87.8%

#17

Claude-4.0-Opus-Thinking

87.8%

#18

Kimi-K2-Instruct

86.7%

#19

Gemini-2.0-Pro-0121

86.7%

#20

Gemini-2.0-Flash

84.4%

#21

Gemini-2.5-Pro-Thinking

84.4%

#22

Gemini-2.5-Pro-0325

84.4%

#23

GPT-4-mini

73.3%

#24

Gemini-2.5-Flash

71.1%

#25

GPT-4.1

66.7%

#26

Gemini-1.5-Pro

66.7%

#27

Llama-3.1-405B

66.7%

#28

Qwen-3

64.4%

#29

GPT-3.5-Turbo

64.4%

#30

Qwen-3-Thinking

64.4%

#31

GPT-4o-0513

62.2%

#32

Grok-4

46.7%

#33

Grok-4-Thinking

46.7%

#34

Grok-3-Beta

46.7%

#35

Grok-3-Mini-Beta

44.4%

#36

DeepSeek-R1

41.1%

#37

DeepSeek-V3

37.8%

#38

OpenAI-O1-mini

31.1%

#39

Mistral-Large-2

22.2%

#40

Cohere-Command-R-Plus

15.6%