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-HateSpeechIncitingViolence

A measure of model refusal for Hate/Toxicity (Level-1: Content Safety Risks, Level-2: Hate/Toxicity) related to hate speech. Includes Level-4 risks targeting various characteristics like race, ethnicity, color, gender, sexual orientation, religion, beliefs, nationality, geographic region, caste, social behaviors, physical characteristics, mental characteristics, personality, health conditions, disability, pregnancy status, genetic information, occupation, and age.

Source:

Model Performance

#1

Claude-4.0-Sonnet

99.9%

#2

Claude-4.0-Sonnet-Thinking

99.9%

#3

Claude-4.0-Opus-Thinking

99.7%

#4

Claude-4.0-Opus

99.7%

#5

Claude-3.5-Sonnet-1022

99.6%

#6

Claude-3.7-Sonnet

99.0%

#7

Claude-3.7-Sonnet-Thinking

99.0%

#8

Claude-3-Opus

98.1%

#9

Claude-3-Sonnet

97.7%

#10

GPT-OSS-120B

97.7%

#11

GPT-4.5

97.5%

#12

Granite-3.0

97.4%

#13

Gemini-2.5-Pro-0325

96.4%

#14

Gemini-2.5-Pro-Thinking

96.4%

#15

Kimi-K2-Instruct

95.8%

#16

Gemini-2.5-Flash

94.3%

#17

GPT-4.1

94.3%

#18

OpenAI-O3-mini-medium

93.9%

#19

Gemini-2.0-Flash

93.8%

#20

OpenAI-O3-medium

92.3%

#21

Gemini-2.0-Pro-0121

92.2%

#22

OpenAI-O1-1217

90.7%

#23

Gemini-1.5-Pro

90.6%

#24

OpenAI-O4-mini-medium

90.1%

#25

Llama-4-Maverick-17B

90.0%

#26

DeepSeek-R1

88.0%

#27

Llama-3.1-405B

87.2%

#28

Qwen-3

86.5%

#29

Qwen-3-Thinking

86.5%

#30

Grok-3-Mini-Beta

84.5%

#31

GPT-4o-0513

80.1%

#32

DeepSeek-V3

74.8%

#33

Grok-3-Beta

73.9%

#34

GPT-4-mini

73.5%

#35

Mistral-Large-2

68.8%

#36

Grok-4

63.8%

#37

Grok-4-Thinking

63.8%

#38

GPT-3.5-Turbo

63.5%

#39

OpenAI-O1-mini

57.5%

#40

Cohere-Command-R-Plus

50.4%